Related papers: S-SimCSE: Sampled Sub-networks for Contrastive Lea…
Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…
Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…
Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn…
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural network approach to detect translational equivalence between…
Recent studies on semi-supervised learning (SSL) have achieved great success. Despite their promising performance, current state-of-the-art methods tend toward increasingly complex designs at the cost of introducing more network components…
While the introduction of contrastive learning frameworks in sentence representation learning has significantly contributed to advancements in the field, it still remains unclear whether state-of-the-art sentence embeddings can capture the…
We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for…
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…
Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…
The enhancement of unsupervised learning of sentence representations has been significantly achieved by the utility of contrastive learning. This approach clusters the augmented positive instance with the anchor instance to create a desired…
Recently, open domain multi-turn chatbots have attracted much interest from lots of researchers in both academia and industry. The dominant retrieval-based methods use context-response matching mechanisms for multi-turn response selection.…
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data.…
We propose a sentence-level language model which selects the next sentence in a story from a finite set of fluent alternatives. Since it does not need to model fluency, the sentence-level language model can focus on longer range…
We propose a new application of embedding techniques for problem retrieval in adaptive tutoring. The objective is to retrieve problems whose mathematical concepts are similar. There are two challenges: First, like sentences, problems…
Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning…
In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard parameter sharing are approaches that introduce explicit biases…
We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…
Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…
Network embedding techniques inspired by word2vec represent an effective unsupervised relational learning model. Commonly, by means of a Skip-Gram procedure, these techniques learn low dimensional vector representations of the nodes in a…