Related papers: An Unsupervised Semantic Sentence Ranking Scheme f…
Existing graph- and hypergraph-based algorithms for document summarization represent the sentences of a corpus as the nodes of a graph or a hypergraph in which the edges represent relationships of lexical similarities between sentences.…
The degree of success in document summarization processes depends on the performance of the method used in identifying significant sentences in the documents. The collection of unique words characterizes the major signature of the document,…
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an…
Semantic matching of natural language sentences or identifying the relationship between two sentences is a core research problem underlying many natural language tasks. Depending on whether training data is available, prior research has…
Keyword Extraction is an important task in several text analysis endeavors. In this paper, we present a critical discussion of the issues and challenges ingraph-based keyword extraction methods, along with comprehensive empirical analysis.…
Text simplification is the task of rewriting a text so that it is readable and easily understood. In this paper, we propose a simple yet novel unsupervised sentence simplification system that harnesses parsing structures together with…
We review the task of Sentence Pair Scoring, popular in the literature in various forms - viewed as Answer Sentence Selection, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment, Paraphrasing or e.g. a component…
We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the quality of a summary…
Literature search is critical for any scientific research. Different from Web or general domain search, a large portion of queries in scientific literature search are entity-set queries, that is, multiple entities of possibly different…
Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence…
Reranking algorithms have made progress in improving document retrieval quality by efficiently aggregating relevance judgments generated by large language models (LLMs). However, identifying relevant documents for queries that require…
Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…
We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word and phrase-level…
This paper describes a method for multi-document update summarization that relies on a double maximization criterion. A Maximal Marginal Relevance like criterion, modified and so called Smmr, is used to select sentences that are close to…
Automatic fact-checking systems detect misinformation, such as fake news, by (i) selecting check-worthy sentences for fact-checking, (ii) gathering related information to the sentences, and (iii) inferring the factuality of the sentences.…
Automatic evaluation of semantic rationality is an important yet challenging task, and current automatic techniques cannot well identify whether a sentence is semantically rational. The methods based on the language model do not measure the…
We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by…
In this paper we introduce a method to detect words or phrases in a given sequence of alphabets without knowing the lexicon. Our linear time unsupervised algorithm relies entirely on statistical relationships among alphabets in the input…
We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents…
Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and…