Related papers: Sentence Embeddings for Russian NLU
We critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding ELMo models on raw tokenized corpora and on the corpora with…
Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…
The performance of Neural Machine Translation (NMT) systems often suffers in low-resource scenarios where sufficiently large-scale parallel corpora cannot be obtained. Pre-trained word embeddings have proven to be invaluable for improving…
Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations…
We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation. Our learning algorithm takes an existing lexical vector space and compresses it such that the resulting word embeddings are good…
Legal proceedings take plenty of time and also cost a lot. The lawyers have to do a lot of work in order to identify the different sections of prior cases and statutes. The paper tries to solve the first tasks in AILA2021 (Artificial…
While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic…
Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our…
Sentence Embedding stands as a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large…
The first two tasks of the CLEF 2019 ProtestNews events focused on distinguishing between protest and non-protest related news articles and sentences in a binary classification task. Among the submissions, two well performing models have…
Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key pitfalls of evaluation of sentence embeddings, a currently…
We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex…
This paper presents results of our system for CoMeDi Shared Task, focusing on Subtask 2: Disagreement Ranking. Our system leverages sentence embeddings generated by the paraphrase-xlm-r-multilingual-v1 model, combined with a deep neural…
The evaluation of cross-lingual semantic search models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. We introduce Cross-Lingual Semantic Discrimination (CLSD), a lightweight…
We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for…
Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature. We perform an extensive evaluation of four popular approaches of…
We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention…
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence…
Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…