相关论文: Embodied negation and levels of concreteness: A TM…

In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their…

The nouns of our language refer to either concrete entities (like a table) or abstract concepts (like justice or love), and cognitive psychology has established that concreteness influences how words are processed. Accordingly,…

The role of the motor cortex in perceptual and cognitive functions is highly controversial. Here, we investigated the hypothesis that the motor cortex can be instrumental for translating foreign language vocabulary. Participants were…

Contradictory results about the encoding of the semantic impact of negation in pretrained language models (PLMs). have been drawn recently (e.g. Kassner and Sch{\"u}tze (2020); Gubelmann and Handschuh (2022)). In this paper we focus rather…

How meaning is represented in the brain is still one of the big open questions in neuroscience. Does a word (e.g., bird) always have the same representation, or does the task under which the word is processed alter its representation…

As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We…

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…

Word representation is fundamental in NLP tasks, because it is precisely from the coding of semantic closeness between words that it is possible to think of teaching a machine to understand text. Despite the spread of word embedding…

Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict…

Several methodologies have recently been proposed to evaluate the ability of Pretrained Language Models (PLMs) to interpret negation. In this article, we build on Gubelmann and Handschuh (2022), which studies the modification of PLMs'…

Negation plays an important role in various natural language processing tasks such as Natural Language Inference and Sentiment Analysis tasks. Numerous prior studies have found that contextual text embedding models such as BERT, ELMO,…

Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. We call such responses \textit{strong…

Conversational systems often rely on embedding models for intent classification and intent clustering tasks. The advent of Large Language Models (LLMs), which enable instructional embeddings allowing one to adjust semantics over the…

The representations generated by many models of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people read. However, these decoding results are usually based on the brain's…

This paper explores negative lexical constraining in English to Czech neural machine translation. Negative lexical constraining is used to prohibit certain words or expressions in the translation produced by the neural translation model. We…

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

Do machines and humans process language in similar ways? Recent research has hinted at the affirmative, showing that human neural activity can be effectively predicted using the internal representations of language models (LMs). Although…

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language models (``LLMs'') has not been studied comprehensively. With the…

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been…

Cross-lingual emotional text-to-speech (TTS) aims to produce speech in one language that captures the emotion of a speaker from another language while maintaining the target voice's timbre. This process of cross-lingual emotional speech…