Linear text segmentation is a long-standing problem in natural language processing (NLP), focused on dividing continuous text into coherent and semantically meaningful units. Despite its importance, the task remains challenging due to the complexity of defining topic boundaries, the variability in discourse structure, and the need to balance local coherence with global context. These difficulties hinder downstream applications such as summarization, information retrieval, and question answering. In this work, we introduce SegNSP, framing linear text segmentation as a next sentence prediction (NSP) task. Although NSP has largely been abandoned in modern pre-training, its explicit modeling of sentence-to-sentence continuity makes it a natural fit for detecting topic boundaries. We propose a label-agnostic NSP approach, which predicts whether the next sentence continues the current topic without requiring explicit topic labels, and enhance it with a segmentation-aware loss combined with harder negative sampling to better capture discourse continuity. Unlike recent proposals that leverage NSP alongside auxiliary topic classification, our approach avoids task-specific supervision. We evaluate our model against established baselines on two datasets, CitiLink-Minutes, for which we establish the first segmentation benchmark, and WikiSection. On CitiLink-Minutes, SegNSP achieves a B-$F_1$ of 0.79, closely aligning with human-annotated topic transitions, while on WikiSection it attains a B-F$_1$ of 0.65, outperforming the strongest reproducible baseline, TopSeg, by 0.17 absolute points. These results demonstrate competitive and robust performance, highlighting the effectiveness of modeling sentence-to-sentence continuity for improving segmentation quality and supporting downstream NLP applications.
Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reducing wrongly labeled relations (false positives) while few explore the missing relations that are caused by incompleteness of knowledge base (false negatives). Furthermore, the quantity of negative labels overwhelmingly surpasses the positive ones in previous problem formulations. In this paper, we first provide a thorough analysis of the above challenges caused by negative data.…
Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b). While they found LSTM recurrent networks to underperform word averaging, we present several developments that together produce the opposite conclusion. These include training on sentence pairs rather than phrase pairs, averaging states to represent sequences, and regularizing aggressively. These improve LSTMs in both transfer learning and supervised settings. We also introduce a new recurrent architecture, the Gated Recurrent Averaging Network, that is inspir…
Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents as semantic representations. We argue that documents like Wikipedia pages contain rich visual information, which however can easily be buried by the vast amount of non-visual sentences. To address this issue, we propose a semi-automatic mechanism for visual sentence extraction that leverages the document section headers and the clustering structure of visua…
This paper studies the performances of BERT combined with tree structure in short sentence ranking task. In retrieval-based question answering system, we retrieve the most similar question of the query question by ranking all the questions in datasets. If we want to rank all the sentences by neural rankers, we need to score all the sentence pairs. However it consumes large amount of time. So we design a specific tree for searching and combine deep model to solve this problem. We fine-tune BERT on the training data to get semantic vector or sentence embeddings on the test data. We use all the s…
Universidad Nacional Autónoma de México (UNAM)（墨西哥国立自治大学）；Centro de ciencias genómicas (CCG–UNAM)（基因组科学中心（墨西哥国立自治大学））；Instituto de ingeniería (IIngen–UNAM)（工程研究所（墨西哥国立自治大学））；Laboratoire Informatique d’Avignon (LIA–UAPV)（阿维尼翁计算机科学实验室（阿维尼翁大学））；Centro de investigación en computación (CIC–IPN)（计算机研究中心（国立理工学院））
Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an open question due to complexities of semantic interactions among words. In this paper, we present an embedding method, which is aimed at learning unsupervised sentence representations from unlabeled text. We propose an unsupervised method that models a sentence as a weighted series of word embeddings. The weights of the word embeddings are fitted by using Shan…
The centroid-based model for extractive document summarization is a simple and fast baseline that ranks sentences based on their similarity to a centroid vector. In this paper, we apply this ranking to possible summaries instead of sentences and use a simple greedy algorithm to find the best summary. Furthermore, we show possi- bilities to scale up to larger input docu- ment collections by selecting a small num- ber of sentences from each document prior to constructing the summary. Experiments were done on the DUC2004 dataset for multi-document summarization. We ob- serve a higher performance …
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
In the PDTB-3, several thousand implicit discourse relations were newly annotated \textit{within} individual sentences, adding to the over 15,000 implicit relations annotated \textit{across} adjacent sentences in the PDTB-2. Given that the position of the arguments to these \textit{intra-sentential implicits} is no longer as well-defined as with \textit{inter-sentential implicits}, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different s…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate s…
M Health Information Systems（3M健康信息系统）；Carnegie Mellon University（卡内基梅隆大学）
Scoring the factuality of a generated summary involves measuring the degree to which a target text contains factual information using the input document as support. Given the similarities in the problem formulation, previous work has shown that Natural Language Inference models can be effectively repurposed to perform this task. As these models are trained to score entailment at a sentence level, several recent studies have shown that decomposing either the input document or the summary into sentences helps with factuality scoring. But is fine-grained decomposition always a winning strategy? I…
We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences. The first contribution of this analysis addresses reproducible research: to meaningfully compare different models, their accuracies must be averaged over far more random seeds than what has traditionally been reported. With proper averaging in place, we notice that the distillation model described in arXiv:1603.06318v4 [cs.LG], which incorporates explicit logic rules for sentiment classification, is ineffective. In contrast, using contextualized ELMo embeddings (arXiv…
SKT5SciSumm -- Revisiting Extractive-Generative Approach for Multi-Document Scientific Summarization
University of Information Technology（信息科技大学）；VNU - HCM（胡志明市国家大学）；Deakin University（迪肯大学）；National Institute of Informatics（情报学研究所）；University of Göttingen（哥廷根大学）；University of Würzburg（维尔茨堡大学）
Quality estimation (QE) is the task of automatically evaluating the quality of translations without human-translated references. Calculating BLEU between the input sentence and round-trip translation (RTT) was once considered as a metric for QE, however, it was found to be a poor predictor of translation quality. Recently, various pre-trained language models have made breakthroughs in NLP tasks by providing semantically meaningful word and sentence embeddings. In this paper, we employ semantic embeddings to RTT-based QE. Our method achieves the highest correlations with human judgments, compar…
Peking University（北京大学）；Huazhong University of Science and Technology（华中科技大学）；Microsoft Research（微软研究院）
Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which is called "language embedding". The language embedding can be either added to the word embedding or attached at the beginning of the sentence. It serves as a language-specific signal for the Transformer to capture contextual representations across languages. In this paper, we revisit the use of language embedding and identify several problems in the existing …
CSIRO Data61（澳大利亚联邦科学与工业研究组织Data61）；University of Copenhagen（哥本哈根大学）；Pioneer Centre for AI（人工智能先锋中心）
The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph documents are common and they cannot be efficiently encoded by vanilla Transformer-based models. We compare different Transformer-based Long Document Classification (TrLDC) approaches that aim to mitigate the computational overhead of vanilla transformers to encode much longer text, namely sparse attention and hierarchical encoding methods. We examine several aspects of sparse attention (e.g., size of local attention window,…
Syntactic rules in natural language typically need to make reference to hierarchical sentence structure. However, the simple examples that language learners receive are often equally compatible with linear rules. Children consistently ignore these linear explanations and settle instead on the correct hierarchical one. This fact has motivated the proposal that the learner's hypothesis space is constrained to include only hierarchical rules. We examine this proposal using recurrent neural networks (RNNs), which are not constrained in such a way. We simulate the acquisition of question formation,…
