Jian-yun Nie

Université de Montréal | UdeM · Department of Computer Science and Operations Research

To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers $13$ common text generation tasks and their corresponding $83$ datasets and further incorporates $45$ PLMs covering general, translation,...

As a means to understanding the healthiness of the food environment, obtaining big data (big food and other types) to model the built environment becomes critical. In this paper, we train and test seven different ML methods on bigdata from census data to predict the healthiness of the food environment. We introduce a synthetic ecosystem platform th...

In the prompt-specific holistic score prediction task for Automatic Essay Scoring, the general approaches include pre-trained neural model, coherence model, and hybrid model that incorporate syntactic features with neural model. In this paper, we propose a novel approach to extract and represent essay coherence features with prompt-learning NSP tha...

We study the text generation task under the approach of pre-trained language models (PLMs). Typically, an auto-regressive (AR) method is adopted for generating texts in a token-by-token manner. Despite many advantages of AR generation, it usually suffers from inefficient inference. Therefore, non-autoregressive (NAR) models are proposed to generate...

Contextual information in search sessions is important for capturing users' search intents. Various approaches have been proposed to model user behavior sequences to improve document ranking in a session. Typically, training samples of (search context, document) pairs are sampled randomly in each training epoch. In reality, the difficulty to unders...

Due to the overload of published scientific articles, citation recommendation has long been a critical research problem for automatically recommending the most relevant citations of given articles. Relational topic models (RTMs) have shown promise on citation prediction via joint modeling of document contents and citations. However, existing RTMs c...

Beyond topical relevance, passage ranking for open-domain factoid question answering also requires a passage to contain an answer (answerability). While a few recent studies have incorporated some reading capability into a ranker to account for answerability, the ranker is still hindered by the noisy nature of the training data typically available...

Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is costly to acquire and difficult to define and annotate accurately. In this paper, we propose a novel framework...

Fine-grained sentiment analysis is currently a main focus in the field of natural language processing. In line with the significance of the semantics and the syntax, both semantic- and syntactic-based approaches are dedicatedly devised and developed. However, the highly integrating of the semantic and syntactic information is still challenging, whi...

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and lightweight model that can adapt to various text generation tasks based on PLMs. To fulfill this purpose, the recent pr...

Relation classification between entities is a fundamental problem in knowledge extraction. It aims at determining if a semantic relation holds between a pair of entities based on textual descriptions. In general, the training data for each relation is limited. Distant supervision has thus been widely used to generate abundant weakly labeled data fo...

Generating a text based on a predefined guideline is an interesting but challenging problem. A series of studies have been carried out in recent years. In dialogue systems, researchers have explored driving a dialogue based on a plan, while in story generation, a storyline has also been proved to be useful. In this paper, we address a new task–gene...

Text Generation aims to produce plausible and readable text in human language from input data. The resurgence of deep learning has greatly advanced this field by neural generation models, especially the paradigm of pretrained language models (PLMs). Grounding text generation on PLMs is seen as a promising direction in both academia and industry. In...

Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a user behavior sequence has often been viewed as a definite and exact signal reflecting a user's behavior. In real...

A proactive dialogue system has the ability to proactively lead the conversation. Different from the general chatbots which only react to the user, proactive dialogue systems can be used to achieve some goals, e.g., to recommend some items to the user. Background knowledge is essential to enable smooth and natural transitions in dialogue. In this p...

Deep learning models for automatic readability assessment generally discard linguistic features traditionally used in machine learning models for the task. We propose to incorporate linguistic features into neural network models by learning syntactic dense embeddings based on linguistic features. To cope with the relationships between the features,...

Sentence ordering aims at arranging a list of sentences in the correct order. Based on the observation that sentence order at different distances may rely on different types of information, we devise a new approach based on multi-granular orders between sentences. These orders form multiple constraint graphs, which are then encoded by Graph Isomorp...

We provide a novel perspective on conversational emotion recognition by drawing an analogy between the task and a complete span of quantum measurement. We characterize different steps of quantum measurement in the process of recognizing speakers' emotions in conversation, and stitch them up with a quantum-like neural network. The quantum-like layer...

Grounding human-machine conversation in a document is an effective way to improve the performance of retrieval-based chatbots. However, only a part of the document content may be relevant to help select the appropriate response at a round. It is thus crucial to select the part of document content relevant to the current conversation context. In thi...

Sentence ordering aims to arrange the sentences of a given text in the correct order. Recent work frames it as a ranking problem and applies deep neural networks to it. In this work, we propose a new method, named BERT4SO, by fine-tuning BERT for sentence ordering. We concatenate all sentences and compute their representations by using multiple spe...

Sentence ordering aims at arranging a list of sentences in the correct order. Based on the observation that sentence order at different distances may rely on different types of information, we devise a new approach based on multi-granular orders between sentences. These orders form multiple constraint graphs, which are then encoded by Graph Isomorp...

Grounding human-machine conversation in a document is an effective way to improve the performance of retrieval-based chatbots. However, only a part of the document content may be relevant to help select the appropriate response at a round. It is thus crucial to select the part of document content relevant to the current conversation context. In thi...

Most existing studies on Automated Essay Scoring (AES) focused on a single prompt, and only a few studies have addressed the problem of cross-prompt AES. This paper addresses the key question of how to extract more transferable rating knowledge from multiple source prompts. Different from the common approach which extracts an invariant part among a...

Active learning is an effective approach for tasks with limited labeled data. It samples a small set of data to annotate actively and is widely applied in various AI tasks. It uses an iterative process, during which we utilize the current trained model to evaluate all unlabeled samples and annotate the best samples based on a specific query strateg...

Query understanding bridges the gap and establishes a communication channel between the searcher and the search engine. An important challenge in question understanding is the enhancement of user interaction with the search engine in a more natural way, including spoken language querying, multi-turn search sessions and conversational question answe...

This chapter focuses on how digitization can accelerate convergence in science and innovation, examining how it can support design, operation, and adaptive learning for the system as a whole and for actors along supply chains and markets. It briefly reviews key tenets of convergence science and innovation (CI). The first key enabler of CI is the co...

Distant supervision provides a means to create a large number of weakly labeled data at low cost for relation classification. However, the resulting labeled instances are very noisy, containing data with wrong labels. Many approaches have been proposed to select a subset of reliable instances for neural model training, but they still suffer from no...

Pre-trained language models have been successfully used in response generation for open-domain dialogue. Four main frameworks have been proposed: (1) Transformer-ED using Transformer encoder and decoder separately for source and target sentences; (2) Transformer-Dec using Transformer decoder for both source and target sentences; (3) Transformer-MLM...

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary. Existing approaches exploit BERT encoder and copy-based RNN decoder, where the encoder first predicts the state operation, and then the decoder generates new slot values. However, in this stacked encoder-decoder structure, the operation prediction objecti...

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary, which aims to extract the state from the dialogue. Existing approaches usually concatenate previous dialogue state with dialogue history as the input to a bi-directional Transformer encoder. They rely on the self-attention mechanism of Transformer to conn...

We investigate the general problem of conditioned dialogue, in which a condition label is used as input to designate the type of the target response such as a persona. A major challenge for conditioned dialogue generation is the lack of substantial dialogue data labeled with conditions. Thus, we propose to complement the labeled dialogue data with...

Mining opinion is essential for consistency and persona of a chatbot. However, mining existing opinions suffers from data sparsity. Toward a given entity, we cannot always find a proper sentence that expresses desired sentiment. In this paper, we propose to generate opinion sentences for a given attitude, i.e., an entity and sentiment polarity pair...

Conventional science, technology and innovation (STI) agendas have fueled powerful economic growth and social progress around the world. However, negative outcomes associated with such growth progressively cumulated in a set of interconnected grand challenges like climate change, hunger, and other goals of sustainable development. Societal-scale so...

It is appealing to have a system that generates a story or scripts automatically from a story-line, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this paper, we address a key problem involved in these applications -- guiding a dialogue by a narrative. The proposed...

Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a...

Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a...

Most state-of-the-art named entity recognition systems are designed to process each sentence within a document independently. These systems are easy to confuse entity types when the context information in a sentence is not sufficient enough. To utilize the context information within the whole document, most document-level work let neural networks o...

Recently, many neural retrieval models have been proposed and shown competitive results. In particular, interaction-based models have shown superior performance to traditional models in a number of studies. However, the interactions used as the basic matching signals are between single terms or their embeddings. In reality, a term can often match a...

Human–computer conversation is an active research topic in natural language processing. One of the representative methods to build conversation systems uses the sequence-to-sequence (Seq2seq) model through neural networks. However, with limited input information, the Seq2seq model tends to generate meaningless and trivial responses. It can be great...

Human conversations are often embedded with emotions. To simulate human conversations, the response generated by a chatbot not only has to be topically relevant to the post, but should also carry an appropriate emotion. In this paper, we conduct analysis based on social media data to investigate how emotions influence conversation generation. Based...

Recent deep learning models for information retrieval typically aim to learn features either about the contents of the document and the query, or about the interactions between them. However, the existing literature shows that document ranking depends simultaneously on many factors, including both content and interaction features. The integration o...

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and...

This paper studies graph-based recommendation, where an interaction graph is constructed built from historical records and is lever-aged to alleviate data sparsity and cold start problems. We reveal an early summarization problem in existing graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between u...

This paper studies graph-based recommendation, where an interaction graph is built from historical responses and is leveraged to alleviate data sparsity and cold start problems. We reveal an early summarization problem in previous graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between user-side an...

In e-commerce, users' demands are not only conditioned by their profile and preferences, but also by their recent purchases that may generate new demands, as well as periodical demands that depend on purchases made some time ago. We call them respectively short-term demands and long-term demands. In this paper, we propose a novel self-attentive Con...

Personalized search aims to adapt document ranking to user's personal interests. Traditionally, this is done by extracting click and topical features from historical data in order to construct a user profile. In recent years, deep learning has been successfully used in personalized search due to its ability of automatic feature learning. However, t...

Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and re...

Model construction is a kind of knowledge engineering, and building retrieval models is critical to the success of search engines. This article proposes a new (retrieval) language model, called binary independence language model (BILM). It integrates two document-context based language models together into one by the log-odds ratio where these two...

Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and re...

Presents corrections to author information from the paper, “Characterizing and predicting early reviewers for effective product marketing on e-commerce websites,” (Bai, T., et al), IEEE Trans. Knowl. Data Eng., vol. 30, no. 12, pp. 2271–2284, Dec. 2018.

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is abl...

Recommending the right products is the central problem in recommender systems, but the right products should also be recommended at the right time to meet the demands of users, so as to maximize their values. Users' demands, implying strong purchase intents, can be the most useful way to promote products sales if well utilized. Previous recommendat...

Query suggestion helps search users to efficiently express their information needs and has attracted many studies. Among the different kinds of factors that help improve query suggestion performance, user behavior information is commonly used because user’s information needs are implicitly expressed in their behavior log. However, most existing app...

This is a report on the ninth edition of the \textsl{Conference and Labs of the Evaluation Forum} (CLEF 2018), held in early September 2018, in Avignon, France. CLEF was a four day event combining a Conference and an Evaluation Forum. The Conference featured keynotes by Nicholas Belkin, Julio Gonzalo, and Gabriella Pasi, and presentation of 29 pee...

We describe the state-of-the-art in performance modeling and prediction for Information Retrieval (IR), Natural Language Processing (NLP) and Recommender Systems (RecSys) along with its shortcomings and strengths. We present a framework for further research, identifying five major problem areas: understanding measures, performance analysis, making...

Modern Information Retrieval (IR) systems have become more and more complex, involving a large number of parameters. For example, a system may choose from a set of possible retrieval models (BM25, language model, etc.), or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. Traditionally, these pa...

Context-aware Recommendations (CARS) have attracted a lot of attention recently because of the impact of contextual information on user behaviors. Recent state-of-the-art methods represent the relations between users/items and contexts as a tensor, with which it is difficult to distinguish the impacts of different contextual factors and to model co...

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and...