arXiv subjects

Owen Rambow

Publications and source records attributed to Owen Rambow.

At least 37 records · Page 2Linked to original sources

arXiv2024

Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents

We propose a novel clustering pipeline to detect and characterize influence campaigns from documents. This approach clusters parts of document, detects clusters that likely reflect an influence campaign, and then identifies documents linked to an influence campaign via their association with the high-influence clusters. Our approach outperforms both the direct document-level classification and the direct document-level clustering approach in predicting if a document is part of an influence campaign. We propose various novel techniques to enhance our pipeline, including using an existing event factuality prediction system to obtain document parts, and aggregating multiple clustering experiments to improve the performance of both cluster and document classification. Classifying documents after clustering not only accurately extracts the parts of the documents that are relevant to influence campaigns, but also captures influence campaigns as a coordinated and holistic phenomenon. Our approach makes possible more fine-grained and interpretable characterizations of influence campaigns from documents.

cs.CL↗

arXiv2024

NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions. We introduce NormSage, a framework for addressing the novel task of conversation-grounded multi-lingual, multi-cultural norm discovery, based on language model prompting and self-verification. NormSAGE leverages the expressiveness and implicit knowledge of the pretrained GPT-3 language model backbone, to elicit knowledge about norms through directed questions representing the norm discovery task and conversation context. It further addresses the risk of language model hallucination with a self-verification mechanism ensuring that the norms discovered are correct and are substantially grounded to their source conversations. Evaluation results show that our approach discovers significantly more relevant and insightful norms for conversations on-the-fly compared to baselines (>10+% in Likert scale rating). The norms discovered from Chinese conversation are also comparable to the norms discovered from English conversation in terms of insightfulness and correctness (<3% difference). In addition, the culture-specific norms are promising quality, allowing for 80% accuracy in culture pair human identification. Finally, our grounding process in norm discovery self-verification can be extended for instantiating the adherence and violation of any norm for a given conversation on-the-fly, with explainability and transparency. NormSAGE achieves an AUC of 95.4% in grounding, with natural language explanation matching human-written quality.

cs.CL↗

arXiv2023

Finding Common Ground: Annotating and Predicting Common Ground in Spoken Conversations

When we communicate with other humans, we do not simply generate a sequence of words. Rather, we use our cognitive state (beliefs, desires, intentions) and our model of the audience's cognitive state to create utterances that affect the audience's cognitive state in the intended manner. An important part of cognitive state is the common ground, which is the content the speaker believes, and the speaker believes the audience believes, and so on. While much attention has been paid to common ground in cognitive science, there has not been much work in natural language processing. In this paper, we introduce a new annotation and corpus to capture common ground. We then describe some initial experiments extracting propositions from dialog and tracking their status in the common ground from the perspective of each speaker.

cs.CL↗

arXiv2022

From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains

We present a generalized paradigm for adaptation of propositional analysis (predicate-argument pairs) to new tasks and domains. We leverage an analogy between stances (belief-driven sentiment) and concerns (topical issues with moral dimensions/endorsements) to produce an explanatory representation. A key contribution is the combination of semi-automatic resource building for extraction of domain-dependent concern types (with 2-4 hours of human labor per domain) and an entirely automatic procedure for extraction of domain-independent moral dimensions and endorsement values. Prudent (automatic) selection of terms from propositional structures for lexical expansion (via semantic similarity) produces new moral dimension lexicons at three levels of granularity beyond a strong baseline lexicon. We develop a ground truth (GT) based on expert annotators and compare our concern detection output to GT, to yield 231% improvement in recall over baseline, with only a 10% loss in precision. F1 yields 66% improvement over baseline and 97.8% of human performance. Our lexically based approach yields large savings over approaches that employ costly human labor and model building. We provide to the community a newly expanded moral dimension/value lexicon, annotation guidelines, and GT.

cs.CL↗

arXiv2020

Open-Domain Frame Semantic Parsing Using Transformers

Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such as syntactic and semantic parsing). In this paper, we explore multi-task learning of all subtasks with transformer-based models. We show that a purely generative encoder-decoder architecture handily beats the previous state of the art in FrameNet 1.7 parsing, and that a mixed decoding multi-task approach achieves even better performance. Finally, we show that the multi-task model also outperforms recent state of the art systems for PropBank SRL parsing on the CoNLL 2012 benchmark.

cs.CL↗

arXiv2020

To Test Machine Comprehension, Start by Defining Comprehension

Many tasks aim to measure machine reading comprehension (MRC), often focusing on question types presumed to be difficult. Rarely, however, do task designers start by considering what systems should in fact comprehend. In this paper we make two key contributions. First, we argue that existing approaches do not adequately define comprehension; they are too unsystematic about what content is tested. Second, we present a detailed definition of comprehension -- a "Template of Understanding" -- for a widely useful class of texts, namely short narratives. We then conduct an experiment that strongly suggests existing systems are not up to the task of narrative understanding as we define it.

cs.CL↗

arXiv2019

Syntax-aware Neural Semantic Role Labeling with Supertags

We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish. We use a BiLSTM to tag the text with supertags extracted from dependency parses, and we feed these supertags, along with words and parts of speech, into a deep highway BiLSTM for semantic role labeling. Our model combines the strengths of earlier models that performed SRL on the basis of a full dependency parse with more recent models that use no syntactic information at all. Our local and non-ensemble model achieves state-of-the-art performance on the CoNLL 09 English and Spanish datasets. SRL models benefit from syntactic information, and we show that supertagging is a simple, powerful, and robust way to incorporate syntax into a neural SRL system.

cs.CL↗

arXiv2018

Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions

Understanding how social power structures affect the way we interact with one another is of great interest to social scientists who want to answer fundamental questions about human behavior, as well as to computer scientists who want to build automatic methods to infer the social contexts of interactions. In this paper, we employ advancements in extra-propositional semantics extraction within NLP to study how author commitment reflects the social context of an interaction. Specifically, we investigate whether the level of commitment expressed by individuals in an organizational interaction reflects the hierarchical power structures they are part of. We find that subordinates use significantly more instances of non-commitment than superiors. More importantly, we also find that subordinates attribute propositions to other agents more often than superiors do --- an aspect that has not been studied before. Finally, we show that enriching lexical features with commitment labels captures important distinctions in social meanings.

cs.CL↗

arXiv2018

End-to-end Graph-based TAG Parsing with Neural Networks

We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.

cs.CL↗

arXiv2017

Leveraging Sparse and Dense Feature Combinations for Sentiment Classification

Neural networks are one of the most popular approaches for many natural language processing tasks such as sentiment analysis. They often outperform traditional machine learning models and achieve the state-of-art results on most tasks. However, many existing deep learning models are complex, difficult to train and provide a limited improvement over simpler methods. We propose a simple, robust and powerful model for sentiment classification. This model outperforms many deep learning models and achieves comparable results to other deep learning models with complex architectures on sentiment analysis datasets. We publish the code online.

cs.CL↗

arXiv2017

Dialog Structure Through the Lens of Gender, Gender Environment, and Power

Understanding how the social context of an interaction affects our dialog behavior is of great interest to social scientists who study human behavior, as well as to computer scientists who build automatic methods to infer those social contexts. In this paper, we study the interaction of power, gender, and dialog behavior in organizational interactions. In order to perform this study, we first construct the Gender Identified Enron Corpus of emails, in which we semi-automatically assign the gender of around 23,000 individuals who authored around 97,000 email messages in the Enron corpus. This corpus, which is made freely available, is orders of magnitude larger than previously existing gender identified corpora in the email domain. Next, we use this corpus to perform a large-scale data-oriented study of the interplay of gender and manifestations of power. We argue that, in addition to one's own gender, the "gender environment" of an interaction, i.e., the gender makeup of one's interlocutors, also affects the way power is manifested in dialog. We focus especially on manifestations of power in the dialog structure --- both, in a shallow sense that disregards the textual content of messages (e.g., how often do the participants contribute, how often do they get replies etc.), as well as the structure that is expressed within the textual content (e.g., who issues requests and how are they made, whose requests get responses etc.). We find that both gender and gender environment affect the ways power is manifested in dialog, resulting in patterns that reveal the underlying factors. Finally, we show the utility of gender information in the problem of automatically predicting the direction of power between pairs of participants in email interactions.

cs.CL↗

arXiv2016

Using Natural Language Processing and Qualitative Analysis to Intervene in Gang Violence: A Collaboration Between Social Work Researchers and Data Scientists

The U.S. has the highest rate of firearm-related deaths when compared to other industrialized countries. Violence particularly affects low-income, urban neighborhoods in cities like Chicago, which saw a 40% increase in firearm violence from 2014 to 2015 to more than 3,000 shooting victims. While recent studies have found that urban, gang-involved individuals curate a unique and complex communication style within and between social media platforms, organizations focused on reducing gang violence are struggling to keep up with the growing complexity of social media platforms and the sheer volume of data they present. In this paper, describe the Digital Urban Violence Analysis Approach (DUVVA), a collaborative qualitative analysis method used in a collaboration between data scientists and social work researchers to develop a suite of systems for decoding the high- stress language of urban, gang-involved youth. Our approach leverages principles of grounded theory when analyzing approximately 800 tweets posted by Chicago gang members and participation of youth from Chicago neighborhoods to create a language resource for natural language processing (NLP) methods. In uncovering the unique language and communication style, we developed automated tools with the potential to detect aggressive language on social media and aid individuals and groups in performing violence prevention and interruption.

cs.CY↗

arXiv2015

Statistical modality tagging from rule-based annotations and crowdsourcing

We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for the overwhelming majority of sentences. We investigate an approach to automatically training a modality tagger where we first gathered sentences based on a high-recall simple rule-based modality tagger and then provided these sentences to Mechanical Turk annotators for further annotation. We used the resulting set of training data to train a precise modality tagger using a multi-class SVM that delivers good performance.

cs.CL↗

arXiv2013

LDC Arabic Treebanks and Associated Corpora: Data Divisions Manual

The Linguistic Data Consortium (LDC) has developed hundreds of data corpora for natural language processing (NLP) research. Among these are a number of annotated treebank corpora for Arabic. Typically, these corpora consist of a single collection of annotated documents. NLP research, however, usually requires multiple data sets for the purposes of training models, developing techniques, and final evaluation. Therefore it becomes necessary to divide the corpora used into the required data sets (divisions). This document details a set of rules that have been defined to enable consistent divisions for old and new Arabic treebanks (ATB) and related corpora.

cs.CL↗

arXiv1996

Synchronous Models of Language

In synchronous rewriting, the productions of two rewriting systems are paired and applied synchronously in the derivation of a pair of strings. We present a new synchronous rewriting system and argue that it can handle certain phenomena that are not covered by existing synchronous systems. We also prove some interesting formal/computational properties of our system.

cmp-lg↗

arXiv1995

D-Tree Grammars

DTG are designed to share some of the advantages of TAG while overcoming some of its limitations. DTG involve two composition operations called subsertion and sister-adjunction. The most distinctive feature of DTG is that, unlike TAG, there is complete uniformity in the way that the two DTG operations relate lexical items: subsertion always corresponds to complementation and sister-adjunction to modification. Furthermore, DTG, unlike TAG, can provide a uniform analysis for em wh-movement in English and Kashmiri, despite the fact that the em wh element in Kashmiri appears in sentence-second position, and not sentence-initial position as in English.

cmp-lg↗

arXiv1995

A Processing Model for Free Word Order Languages

Like many verb-final languages, Germn displays considerable word-order freedom: there is no syntactic constraint on the ordering of the nominal arguments of a verb, as long as the verb remains in final position. This effect is referred to as ``scrambling'', and is interpreted in transformational frameworks as leftward movement of the arguments. Furthermore, arguments from an embedded clause may move out of their clause; this effect is referred to as ``long-distance scrambling''. While scrambling has recently received considerable attention in the syntactic literature, the status of long-distance scrambling has only rarely been addressed. The reason for this is the problematic status of the data: not only is long-distance scrambling highly dependent on pragmatic context, it also is strongly subject to degradation due to processing constraints. As in the case of center-embedding, it is not immediately clear whether to assume that observed unacceptability of highly complex sentences is due to grammatical restrictions, or whether we should assume that the competence grammar does not place any restrictions on scrambling (and that, therefore, all such sentences are in fact grammatical), and the unacceptability of some (or most) of the grammatically possible word orders is due to processing limitations. In this paper, we will argue for the second view by presenting a processing model for German.

cmp-lg↗

arXiv1994

The Linguistic Relevance of Quasi-Trees

We discuss two constructions (long scrambling and ECM verbs) which challenge most syntactic theories (including traditional TAG approaches) since they seem to require exceptional mechanisms and postulates. We argue that these constructions should in fact be analyzed in a similar manner, namely as involving a verb which selects for a ``defective'' complement. These complements are defective in that they lack certain Case-assigning abilities (represented as functional heads). The constructions differ in how many such abilities are lacking. Following the previous analysis of scrambling of Rambow (1994), we propose a TAG analysis based on quasi-trees.

cmp-lg↗