Related papers: REGMAPR - Text Matching Made Easy

Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the…

Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…

In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates…

Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these…

This paper studies Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models…

Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine…

The ability to describe images with natural language sentences is the hallmark for image and language understanding. Such a system has wide ranging applications such as annotating images and using natural sentences to search for images.In…

Recurrent Neural Networks (RNNs) are widely used in the field of natural language processing (NLP), ranging from text categorization to question answering and machine translation. However, RNNs generally read the whole text from beginning…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Paraphrase detection is an important task in text analytics with numerous applications such as plagiarism detection, duplicate question identification, and enhanced customer support helpdesks. Deep models have been proposed for representing…

Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned…

Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…

The first step in most corpus-based multilingual NLP work is to construct a detailed map of the correspondence between a text and its translation. Several automatic methods for this task have been proposed in recent years. Yet even the best…