Figure 2 - uploaded by Yang Xu
Content may be subject to copyright.
Mean model precision vs. Wu-Palmer distance between WordNet synsets associated with fullypartitioned tokens.
Source publication
Humans often make creative use of words to express novel senses. A long-standing effort in natural language processing has been focusing on word sense disambiguation (WSD), but little has been explored about how the sense inventory of a word may be extended toward novel meanings. We present a paradigm of word sense extension (WSE) that enables word...
Context in source publication
Context 1
... each source-target partitioned token pair (t 0 , t * ), we quantify their degree of conceptual relatedness as the mean Wu-Palmer semantic distance ( Wu and Palmer, 1994) between the WordNet synset of the target sense denoted by t * and the synset of each existing source sense of t 0 . Figure 2 shows the performance of 4 WSE model variants on predicting sense pairs binned with respect to their degree of conceptual similarity. We observe that the WSE models generally make better predictions on source-target token pairs that are semantically more related (e.g., metonymy), and perform less well on examples where the target sense is conceptually very different to the existing source senses (e.g., strong metaphor or homonymy). ...
Similar publications
Humans often make creative use of words to express novel senses. A long-standing effort in natural language processing has been focusing on word sense disambiguation (WSD), but little has been explored about how the sense inventory of a word may be extended toward novel meanings. We present a paradigm of word sense extension (WSE) that enables word...
The increase in the popularity of code mixed languages has resulted in the need to engineer language models for the same. Unlike pure languages , code-mixed languages lack clear grammatical structures, leading to ambiguous sentence constructions. This ambiguity presents significant challenges for natural language processing tasks, including syntact...
Many less-resourced languages struggle with a lack of large, task-specific datasets that are required for solving relevant tasks with modern transformer-based large language models (LLMs). On the other hand, many linguistic resources, such as dictionaries, are rarely used in this context despite their large information contents. We show how LLMs ca...
The level and volume of automatic computerized processing of linguistic information has become one of the most important criteria for measuring whether a country has entered the information society. The study begins with statistical linguistics and aims to process complicated Chinese information. In this paper, after establishing the word database...
This paper describes our zero-shot approaches for the Visual Word Sense Disambiguation (VWSD) Task in English. Our preliminary study shows that the simple approach of matching candidate images with the phrase using CLIP suffers from the many-to-many nature of image-text pairs. We find that the CLIP text encoder may have limited abilities in capturi...
Citations
Regular polysemes are sets of ambiguous words that all share the same relationship between their meanings, such as CHICKEN and LOBSTER both referring to an animal or its meat. To probe how a distributional semantic model, here exemplified by bidirectional encoder representations from transformers (BERT), represents regular polysemy, we analyzed whether its embeddings support answering sense analogy questions similar to “is the mapping between CHICKEN (as an animal) and CHICKEN (as a meat) similar to that which maps between LOBSTER (as an animal) to LOBSTER (as a meat)?” We did so using the LRcos model, which combines a logistic regression classifier of different categories (e.g., animal vs. meat) with a measure of cosine similarity. We found that (a) the model was sensitive to the shared structure within a given regular relationship; (b) the shared structure varies across different regular relationships (e.g., animal/meat vs. location/organization), potentially reflective of a “regularity continuum;” (c) some high‐order latent structure is shared across different regular relationships, suggestive of a similar latent structure across different types of relationships; and (d) there is a lack of evidence for the aforementioned effects being explained by meaning overlap. Lastly, we found that both components of the LRcos model made important contributions to accurate responding and that a variation of this method could yield an accuracy boost of 10% in answering sense analogy questions. These findings enrich previous theoretical work on regular polysemy with a computationally explicit theory and methods, and provide evidence for an important organizational principle for the mental lexicon and the broader conceptual knowledge system.
