Related papers: Sentence Embedding Alignment for Lifelong Relation…

Implicit discourse relations bind smaller linguistic units into coherent texts. Automatic sense prediction for implicit relations is hard, because it requires understanding the semantics of the linked arguments. Furthermore, annotated…

We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks. We also describe a new benchmark, which is much larger and…

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be…

Sentence-level relation extraction mainly aims to classify the relation between two entities in a sentence. The sentence-level relation extraction corpus often contains data that are difficult for the model to infer or noise data. In this…

State-of-the-art methods for relation extraction consider the sentential context by modeling the entire sentence. However, syntactic indicators, certain phrases or words like prepositions that are more informative than other words and may…

Effectively training language models on long inputs poses many technical challenges. As a cost consideration, languages models are pretrained on a fixed sequence length before being adapted to longer sequences. We explore various methods…

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…

Relation extraction task is a crucial and challenging aspect of Natural Language Processing. Several methods have surfaced as of late, exhibiting notable performance in addressing the task; however, most of these approaches rely on vast…

Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with…

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…

Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding…

Continual learning refers to the capability of a machine learning model to learn and adapt to new information, without compromising its performance on previously learned tasks. Although several studies have investigated continual learning…

Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that catastrophic forgetting arises from the model's lack of…

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Sentence embedding is an effective feature representation for most deep learning-based NLP tasks. One prevailing line of methods is using recursive latent tree-structured networks to embed sentences with task-specific structures. However,…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…