Related papers: Polysemanticity or Polysemy? Lexical Identity Conf…
Symbolic systems operate over precise identities: variables denote specific objects, pointers target precise memory locations, and database keys refer to singular records. Neural embeddings generalize by compressing away semantic detail,…
Discovering whether words are semantically related and identifying the specific semantic relation that holds between them is of crucial importance for NLP as it is essential for tasks like query expansion in IR. Within this context,…
Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have employed correlational…
We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information. Our model consists of an encoder, which uses monolingual and bilingual context (i.e. a parallel sentence) to choose a…
Modern transformer-based neural architectures yield impressive results in nearly every NLP task and Word Sense Disambiguation, the problem of discerning the correct sense of a word in a given context, is no exception. State-of-the-art…
Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of…
Why do brains and deep networks converge on similar representations? Task-optimized artificial neural networks quantitatively predict primate ventral stream responses despite radically different substrates and optimization dynamics. This…
One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…
Why do bilingual speakers code-switch (mix their two languages)? Among the several theories that attempt to explain this natural and ubiquitous phenomenon, the Triggering Hypothesis relates code-switching to the presence of lexical…
NLP research on aligning lexical representation spaces to one another has so far focused on aligning language spaces in their entirety. However, cognitive science has long focused on a local perspective, investigating whether translation…
We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\boldsymbol x \in \mathbb R^d$, $r$ hidden units with weights $\{\boldsymbol w_i\}_{1\le…
Natural Language Inference (NLI) is the task of inferring whether the hypothesis can be justified by the given premise. Basically, we classify the hypothesis into three labels(entailment, neutrality and contradiction) given the premise. NLI…
Throughout language history, words are borrowed from one language to another and gradually become integrated into the recipient's lexicon. Speakers can often differentiate these loanwords from native vocabulary, particularly in bilingual…
Evaluation of multimodal reasoning models is typically reduced to a single accuracy score, implicitly treating reasoning as a unitary capability. We introduce MathLens, a benchmark of textbook-style geometry problems that exposes this…
Unsupervised learned representations of polysemous words generate a large of pseudo multi senses since unsupervised methods are overly sensitive to contextual variations. In this paper, we address the pseudo multi-sense detection for word…
The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs, is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that…
Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by…
Slanted news coverage, also called media bias, can heavily influence how news consumers interpret and react to the news. To automatically identify biased language, we present an exploratory approach that compares the context of related…
How universal is human conceptual structure? The way concepts are organized in the human brain may reflect distinct features of cultural, historical, and environmental background in addition to properties universal to human cognition.…
An interesting behavior in large language models (LLMs) is prompt sensitivity. When provided with different but semantically equivalent versions of the same prompt, models may produce very different distributions of answers. This suggests…