Related papers: SentEval: An Evaluation Toolkit for Universal Sent…
In natural language processing, word-sense disambiguation (WSD) is an open problem concerned with identifying the correct sense of words in a particular context. To address this problem, we introduce a novel knowledge-based WSD system. We…
Semantic similarity measures are a key component in natural language processing tasks such as document analysis, requirement matching, and user input interpretation. However, the performance of individual measures varies considerably across…
Analyzing the pattern of semantic variation in long real-world texts such as books or transcripts is interesting from the stylistic, cognitive, and linguistic perspectives. It is also useful for applications such as text segmentation,…
Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…
Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension. However, complete words and phrases composed of several tokens are often the fundamental units for…
Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases. Past work on examining inappropriate biases has largely focused on just individual systems. Further, there is no benchmark dataset…
One popular method for quantitatively evaluating the utility of sentence embeddings involves using them in downstream language processing tasks that require sentence representations as input. One simple such task is classification, where…
Large Language Model (LLM) evaluation is currently one of the most important areas of research, with existing benchmarks proving to be insufficient and not completely representative of LLMs' various capabilities. We present a curated…
By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…
The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…
We present TransEvalnia, a prompting-based translation evaluation and ranking system that uses reasoning in performing its evaluations and ranking. This system presents fine-grained evaluations based on a subset of the Multidimensional…
We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. ESPnet-ST is a new project inside end-to-end speech processing toolkit, ESPnet, which integrates or newly…
Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple…
Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under…
Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and…
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…
The paper proposes the task of universal semantic tagging---tagging word tokens with language-neutral, semantically informative tags. We argue that the task, with its independent nature, contributes to better semantic analysis for…
Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be…
Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability…
Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…