In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages. We propose a knowledge-trans
fer approach that heuristically induces chunk labels from state-of-the-art unsupervised parsing models; a hierarchical recurrent neural network (HRNN) learns from such induced chunk labels to smooth out the noise of the heuristics. Experiments show that our approach largely bridges the gap between supervised and unsupervised chunking.
Stereotypical character roles-also known as archetypes or dramatis personae-play an important function in narratives: they facilitate efficient communication with bundles of default characteristics and associations and ease understanding of those cha
racters' roles in the overall narrative. We present a fully unsupervised k-means clustering approach for learning stereotypical roles given only structural plot information. We demonstrate the technique on Vladimir Propp's structural theory of Russian folktales (captured in the extended ProppLearner corpus, with 46 tales), showing that our approach can induce six out of seven of Propp's dramatis personae with F1 measures of up to 0.70 (0.58 average), with an additional category for minor characters. We have explored various feature sets and variations of a cluster evaluation method. The best-performing feature set comprises plot functions, unigrams, tf-idf weights, and embeddings over coreference chain heads. Roles that are mentioned more often (Hero, Villain), or have clearly distinct plot patterns (Princess) are more strongly differentiated than less frequent or distinct roles (Dispatcher, Helper, Donor). Detailed error analysis suggests that the quality of the coreference chain and plot functions annotations are critical for this task. We provide all our data and code for reproducibility.
Conversations are often held in laboratories and companies. A summary is vital to grasp the content of a discussion for people who did not attend the discussion. If the summary is illustrated as an argument structure, it is helpful to grasp the discu
ssion's essentials immediately. Our purpose in this paper is to predict a link structure between nodes that consist of utterances in a conversation: classification of each node pair into linked'' or not-linked.'' One approach to predict the structure is to utilize machine learning models. However, the result tends to over-generate links of nodes. To solve this problem, we introduce a two-step method to the structure prediction task. We utilize a machine learning-based approach as the first step: a link prediction task. Then, we apply a score-based approach as the second step: a link selection task. Our two-step methods dramatically improved the accuracy as compared with one-step methods based on SVM and BERT.
Accurate recovery of predicate-argument structure from a Universal Dependency (UD) parse is central to downstream tasks such as extraction of semantic roles or event representations. This study introduces compchains, a categorization of the hierarchy
of predicate dependency relations present within a UD parse. Accuracy of compchain classification serves as a proxy for measuring accurate recovery of predicate-argument structure from sentences with embedding. We analyzed the distribution of compchains in three UD English treebanks, EWT, GUM and LinES, revealing that these treebanks are sparse with respect to sentences with predicate-argument structure that includes predicate-argument embedding. We evaluated the CoNLL 2018 Shared Task UDPipe (v1.2) baseline (dependency parsing) models as compchain classifiers for the EWT, GUMS and LinES UD treebanks. Our results indicate that these three baseline models exhibit poorer performance on sentences with predicate-argument structure with more than one level of embedding; we used compchains to characterize the errors made by these parsers and present examples of erroneous parses produced by the parser that were identified using compchains. We also analyzed the distribution of compchains in 58 non-English UD treebanks and then used compchains to evaluate the CoNLL'18 Shared Task baseline model for each of these treebanks. Our analysis shows that performance with respect to compchain classification is only weakly correlated with the official evaluation metrics (LAS, MLAS and BLEX). We identify gaps in the distribution of compchains in several of the UD treebanks, thus providing a roadmap for how these treebanks may be supplemented. We conclude by discussing how compchains provide a new perspective on the sparsity of training data for UD parsers, as well as the accuracy of the resulting UD parses.
Machine reading comprehension is a challenging task especially for querying documents with deep and interconnected contexts. Transformer-based methods have shown advanced performances on this task; however, most of them still treat documents as a fla
t sequence of tokens. This work proposes a new Transformer-based method that reads a document as tree slices. It contains two modules for identifying more relevant text passage and the best answer span respectively, which are not only jointly trained but also jointly consulted at inference time. Our evaluation results show that our proposed method outperforms several competitive baseline approaches on two datasets from varied domains.
Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-huma
n interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples (who-doing-what'') in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-the-art methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/GT-SALT/Structure-Aware-BART.
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating t
he detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery. News editorial is a genre of persuasive text, where the
argumentation structure is usually implicit. However, the arguments presented in an editorial typically center around a concise, focused thesis, which we refer to as their perspective. MultiOpEd aims at supporting the study of multiple tasks relevant to automatic perspective discovery, where a system is expected to produce a single-sentence thesis statement summarizing the arguments presented. We argue that identifying and abstracting such natural language perspectives from editorials is a crucial step toward studying the implicit argumentation structure in news editorials. We first discuss the challenges and define a few conceptual tasks towards our goal. To demonstrate the utility of MultiOpEd and the induced tasks, we study the problem of perspective summarization in a multi-task learning setting, as a case study. We show that, with the induced tasks as auxiliary tasks, we can improve the quality of the perspective summary generated. We hope that MultiOpEd will be a useful resource for future studies on argumentation in the news editorial domain.
Neural language models, including transformer-based models, that are pre-trained on very large corpora became a common way to represent text in various tasks, including recognition of textual semantic relations, e.g. Cross-document Structure Theory.
Pre-trained models are usually fine tuned to downstream tasks and the obtained vectors are used as an input for deep neural classifiers. No linguistic knowledge obtained from resources and tools is utilised. In this paper we compare such universal approaches with a combination of rich graph-based linguistically motivated sentence representation and a typical neural network classifier applied to a task of recognition of CST relation in Polish. The representation describes selected levels of the sentence structure including description of lexical meanings on the basis of the wordnet (plWordNet) synsets and connected SUMO concepts. The obtained results show that in the case of difficult relations and medium size training corpus semantically enriched text representation leads to significantly better results.
Natural Language Processing tools and resources have been so far mainly created and trained for standard varieties of language. Nowadays, with the use of large amounts of data gathered from social media, other varieties and registers need to be proce
ssed, which may present other challenges and difficulties. In this work, we focus on English and we present a preliminary analysis by comparing the TwitterAAE corpus, which is annotated for ethnicity, and WordNet by quantifying and explaining the online language that WordNet misses.
