Word embeddings are ubiquitous in NLP and information retrieval, but it’s unclear what they represent when the word is polysemous, i.e., has multiple senses. Here it is shown that multiple word senses reside in linear superposition within the word embedding and can be recovered by simple sparse coding. The success of the method —which applies to several embedding methods including word2vec— is ...

This paper explores factors correlating with lack of inter-annotator agreement on a word sense disambiguation (WSD) task taken from SENSEVAL-2. Twenty-seven subjects were given a series of tasks requiring word sense judgments. Subjects were asked to judge the applicability of word senses to polysemous words used in context. Metrics of lexical ability were evaluated as predictors of agreement be...

This paper discusses the problem of automated lexicography. In the corpus-based approach, a lexicographer has to manually group contexts of a target word into clusters in order to identify word senses. When a large number of the contexts is given, this process becomes a tedious and time-consuming task. To overcome this problem, we propose an efficient technique based on unsupervised clustering....

Words are polysemous. However, most approaches to representation learning for lexical semantics assign a single vector to every surface word type. Meanwhile, lexical ontologies such as WordNet provide a source of complementary knowledge to distributional information, including a word sense inventory. In this paper we propose two novel and general approaches for generating sense-specific word em...

Given a parallel corpus, if two distinct words in language A, a1 and a2, are aligned to the same word b1 in language B, then this might signal that b1 is polysemous, or it might signal a1 and a2 are synonyms. Both assumptions with successful work have been put forward in the literature. We investigate these assumptions, along with other questions of word sense, by looking at sampled parallel se...

Previous research has indicated that when a polysemous word appears two or more times in a discourse, it is extremely likely that they will all share the same sense [Gale et al. 92]. However, those results were based on a coarse-grained distinction between senses (e.g, sentence in the sense of a ‘prison sentence’ vs. a ‘grammatical sentence’). We report on an analysis of multiple senses within ...

Community question answering (cQA), which provides a platform for people with diverse background to share information and knowledge, has become an increasingly popular research topic. In this paper, we focus on the task of question retrieval. The key problem of question retrieval is to measure the similarity between the queried questions and the historical questions which have been solved by ot...

Vector representations of words have heralded a transformational approach to classical problems in NLP; the most popular example is word2vec. However, a single vector does not suffice to model the polysemous nature of many (frequent) words, i.e., words with multiple meanings. In this paper, we propose a three-fold approach for unsupervised polysemy modeling: (a) context representations, (b) sen...

The accurate exploration of the sentiment information in comments for Massive Open Online Courses (MOOC) courses plays an important role improving its curricular quality and promoting MOOC platform’s sustainable development. At present, most analyses are actually studies extensive sense, while relatively less attention is paid to such intensive issues as polysemous word familiar with upgraded s...

Classically, semantic theories have assumed that words are endowed with universal, immutable meanings. This assumption is not tenable when modeling natural language dialogue; far from treating word meanings as fixed entities, linguistic agents are constantly coordinating useful semantic conventions. They disambiguate polysemous words, construct ad hoc interpretations particular to their communi...