This paper presents a technique for the identification of participant slots in English language contracts. Taking inspiration from unsupervised slot extraction techniques, the system presented here uses a supervised approach to identify terms used to
refer to a genre-specific slot in novel contracts. We evaluate the system in multiple feature configurations to demonstrate that the best performing system in both genres of contracts omits the exact mention form from consideration---even though such mention forms are often the name of the slot under consideration---and is instead based solely on the dependency label and parent; in other words, a more reliable quantification of a party's role in a contract is found in what they do rather than what they are named.
Paraphrase identification (PI), a fundamental task in natural language processing, is to identify whether two sentences express the same or similar meaning, which is a binary classification problem. Recently, BERT-like pre-trained language models hav
e been a popular choice for the frameworks of various PI models, but almost all existing methods consider general domain text. When these approaches are applied to a specific domain, existing models cannot make accurate predictions due to the lack of professional knowledge. In light of this challenge, we propose a novel framework, namely , which can leverage the external unstructured Wikipedia knowledge to accurately identify paraphrases. We propose to mine outline knowledge of concepts related to given sentences from Wikipedia via BM25 model. After retrieving related outline knowledge, makes predictions based on both the semantic information of two sentences and the outline knowledge. Besides, we propose a gating mechanism to aggregate the semantic information-based prediction and the knowledge-based prediction. Extensive experiments are conducted on two public datasets: PARADE (a computer science domain dataset) and clinicalSTS2019 (a biomedical domain dataset). The results show that the proposed outperforms state-of-the-art methods.
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
gue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.
Training a robust and reliable deep learning model requires a large amount of data. In the crisis domain, building deep learning models to identify actionable information from the huge influx of data posted by eyewitnesses of crisis events on social
media, in a time-critical manner, is central for fast response and relief operations. However, building a large, annotated dataset to train deep learning models is not always feasible in a crisis situation. In this paper, we investigate a multi-task learning approach to concurrently leverage available annotated data for several related tasks from the crisis domain to improve the performance on a main task with limited annotated data. Specifically, we focus on using multi-task learning to improve the performance on the task of identifying location mentions in crisis tweets.
Recent metaphor identification approaches mainly consider the contextual text features within a sentence or introduce external linguistic features to the model. But they usually ignore the extra information that the data can provide, such as the cont
extual metaphor information and broader discourse information. In this paper, we propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level. At the sentence level, we leverage the metaphor information of words that except the target word in the sentence to strengthen the reasoning ability of our model via a novel label-enhanced contextualized representation. At the discourse level, the position-aware global memory network is adopted to learn long-range dependency among the same words within a discourse. Finally, our model combines the representations obtained from these two parts. The experiment results on two tasks of the VUA dataset show that our model outperforms every other state-of-the-art method that also does not use any external knowledge except what the pre-trained language model contains.
Quality Estimation (QE) for Machine Translation has been shown to reach relatively high accuracy in predicting sentence-level scores, relying on pretrained contextual embeddings and human-produced quality scores. However, the lack of explanations alo
ng with decisions made by end-to-end neural models makes the results difficult to interpret. Furthermore, word-level annotated datasets are rare due to the prohibitive effort required to perform this task, while they could provide interpretable signals in addition to sentence-level QE outputs. In this paper, we propose a novel QE architecture which tackles both the word-level data scarcity and the interpretability limitations of recent approaches. Sentence-level and word-level components are jointly pretrained through an attention mechanism based on synthetic data and a set of MT metrics embedded in a common space. Our approach is evaluated on the Eval4NLP 2021 shared task and our submissions reach the first position in all language pairs. The extraction of metric-to-input attention weights show that different metrics focus on different parts of the source and target text, providing strong rationales in the decision-making process of the QE model.
The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language identification ha
s dealt with English. To address this shortcoming, we introduce MOLD, the Marathi Offensive Language Dataset. MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in low-resource Indo-Aryan languages. We present results from several machine learning experiments on this dataset, including zero-short and other transfer learning experiments on state-of-the-art cross-lingual transformers from existing data in Bengali, English, and Hindi.
In this paper, we investigate the Domain Generalization (DG) problem for supervised Paraphrase Identification (PI). We observe that the performance of existing PI models deteriorates dramatically when tested in an out-of-distribution (OOD) domain. We
conjecture that it is caused by shortcut learning, i.e., these models tend to utilize the cue words that are unique for a particular dataset or domain. To alleviate this issue and enhance the DG ability, we propose a PI framework based on Optimal Transport (OT). Our method forces the network to learn the necessary features for all the words in the input, which alleviates the shortcut learning problem. Experimental results show that our method improves the DG ability for the PI models.
Bengali is a low-resource language that lacks tools and resources for profane and obscene textual content detection. Until now, no lexicon exists for detecting obscenity in Bengali social media text. This study introduces a Bengali obscene lexicon co
nsisting of over 200 Bengali terms, which can be considered filthy, slang, profane or obscene. A semi-automatic methodology is presented for developing the profane lexicon that leverages an obscene corpus, word embedding, and part-of-speech (POS) taggers. The developed lexicon achieves coverage of around 0.85 for obscene and profane content detection in an evaluation dataset. The experimental results imply that the developed lexicon is effective at identifying obscenity in Bengali social media content.
This article describes a system to predict the complexity of words for the Lexical Complexity Prediction (LCP) shared task hosted at SemEval 2021 (Task 1) with a new annotated English dataset with a Likert scale. Located in the Lexical Semantics trac
k, the task consisted of predicting the complexity value of the words in context. A machine learning approach was carried out based on the frequency of the words and several characteristics added at word level. Over these features, a supervised random forest regression algorithm was trained. Several runs were performed with different values to observe the performance of the algorithm. For the evaluation, our best results reported a M.A.E score of 0.07347, M.S.E. of 0.00938, and R.M.S.E. of 0.096871. Our experiments showed that, with a greater number of characteristics, the precision of the classification increases.
