Jamison, Emily K. (2016)
Crowdsource Annotation and Automatic Reconstruction of Online Discussion Threads.
Technische Universität Darmstadt
Dissertation, Erstveröffentlichung
Kurzbeschreibung (Abstract)
Modern communication relies on electronic messages organized in the form of discussion threads. Emails, IMs, SMS, website comments, and forums are all composed of threads, which consist of individual user messages connected by metadata and discourse coherence to messages from other users. Threads are used to display user messages effectively in a GUI such as an email client, providing a background context for understanding a single message. Many messages are meaningless without the context provided by their thread. However, a number of factors may result in missing thread structure, ranging from user mistake (replying to the wrong message), to missing metadata (some email clients do not produce/save headers that fully encapsulate thread structure; and, conversion of archived threads from over repository to another may also result in lost metadata), to covert use (users may avoid metadata to render discussions difficult for third parties to understand). In the field of security, law enforcement agencies may obtain vast collections of discussion turns that require automatic thread reconstruction to understand. For example, the Enron Email Corpus, obtained by the Federal Energy Regulatory Commission during its investigation of the Enron Corporation, has no inherent thread structure.
In this thesis, we will use natural language processing approaches to reconstruct threads from message content. Reconstruction based on message content sidesteps the problem of missing metadata, permitting post hoc reorganization and discussion understanding. We will investigate corpora of email threads and Wikipedia discussions. However, there is a scarcity of annotated corpora for this task. For example, the Enron Emails Corpus contains no inherent thread structure. Therefore, we also investigate issues faced when creating crowdsourced datasets and learning statistical models of them. Several of our findings are applicable for other natural language machine classification tasks, beyond thread reconstruction.
We will divide our investigation of discussion thread reconstruction into two parts.
First, we explore techniques needed to create a corpus for our thread reconstruction research. Like other NLP pairwise classification tasks such as Wikipedia discussion turn/edit alignment and sentence pair text similarity rating, email thread disentanglement is a heavily class-imbalanced problem, and although the advent of crowdsourcing has reduced annotation costs, the common practice of crowdsourcing redundancy is too expensive for class-imbalanced tasks. As the first contribution of this thesis, we evaluate alternative strategies for reducing crowdsourcing annotation redundancy for class-imbalanced NLP tasks. We also examine techniques to learn the best machine classifier from our crowdsourced labels. In order to reduce noise in training data, most natural language crowdsourcing annotation tasks gather redundant labels and aggregate them into an integrated label, which is provided to the classifier. However, aggregation discards potentially useful information from linguistically ambiguous instances. For the second contribution of this thesis, we show that, for four of five natural language tasks, filtering of the training dataset based on crowdsource annotation item agreement improves task performance, while soft labeling based on crowdsource annotations does not improve task performance.
Second, we investigate thread reconstruction as divided into the tasks of thread disentanglement and adjacency recognition. We present the Enron Threads Corpus, a newly-extracted corpus of 70,178 multi-email threads with emails from the Enron Email Corpus. In the original Enron Emails Corpus, emails are not sorted by thread. To disentangle these threads, and as the third contribution of this thesis, we perform pairwise classification, using text similarity measures on non-quoted texts in emails. We show that i) content text similarity metrics outperform style and structure text similarity metrics in both a class-balanced and class-imbalanced setting, and ii) although feature performance is dependent on the semantic similarity of the corpus, content features are still effective even when controlling for semantic similarity. To reconstruct threads, it is also necessary to identify adjacency relations among pairs. For the forum of Wikipedia discussions, metadata is not available, and dialogue act typologies, helpful for other domains, are inapplicable. As our fourth contribution, via our experiments, we show that adjacency pair recognition can be performed using lexical pair features, without a dialogue act typology or metadata, and that this is robust to controlling for topic bias of the discussions. Yet, lexical pair features do not effectively model the lexical semantic relations between adjacency pairs. To model lexical semantic relations, and as our fifth contribution, we perform adjacency recognition using extracted keyphrases enhanced with semantically related terms. While this technique outperforms a most frequent class baseline, it fails to outperform lexical pair features or tf-idf weighted cosine similarity. Our investigation shows that this is the result of poor word sense disambiguation and poor keyphrase extraction causing spurious false positive semantic connections.
In concluding this thesis, we also reflect on open issues and unanswered questions remaining after our research contributions, discuss applications for thread reconstruction, and suggest some directions for future work.
Typ des Eintrags: | Dissertation | ||||
---|---|---|---|---|---|
Erschienen: | 2016 | ||||
Autor(en): | Jamison, Emily K. | ||||
Art des Eintrags: | Erstveröffentlichung | ||||
Titel: | Crowdsource Annotation and Automatic Reconstruction of Online Discussion Threads | ||||
Sprache: | Englisch | ||||
Referenten: | Gurevych, Prof. Dr. Iryna ; Fürnkranz, Prof. Dr. Johannes ; Daelemans, Prof. Walter | ||||
Publikationsjahr: | 2016 | ||||
Ort: | Darmstadt, Germany | ||||
Datum der mündlichen Prüfung: | 17 Februar 2016 | ||||
URL / URN: | http://tuprints.ulb.tu-darmstadt.de/5385 | ||||
Kurzbeschreibung (Abstract): | Modern communication relies on electronic messages organized in the form of discussion threads. Emails, IMs, SMS, website comments, and forums are all composed of threads, which consist of individual user messages connected by metadata and discourse coherence to messages from other users. Threads are used to display user messages effectively in a GUI such as an email client, providing a background context for understanding a single message. Many messages are meaningless without the context provided by their thread. However, a number of factors may result in missing thread structure, ranging from user mistake (replying to the wrong message), to missing metadata (some email clients do not produce/save headers that fully encapsulate thread structure; and, conversion of archived threads from over repository to another may also result in lost metadata), to covert use (users may avoid metadata to render discussions difficult for third parties to understand). In the field of security, law enforcement agencies may obtain vast collections of discussion turns that require automatic thread reconstruction to understand. For example, the Enron Email Corpus, obtained by the Federal Energy Regulatory Commission during its investigation of the Enron Corporation, has no inherent thread structure. In this thesis, we will use natural language processing approaches to reconstruct threads from message content. Reconstruction based on message content sidesteps the problem of missing metadata, permitting post hoc reorganization and discussion understanding. We will investigate corpora of email threads and Wikipedia discussions. However, there is a scarcity of annotated corpora for this task. For example, the Enron Emails Corpus contains no inherent thread structure. Therefore, we also investigate issues faced when creating crowdsourced datasets and learning statistical models of them. Several of our findings are applicable for other natural language machine classification tasks, beyond thread reconstruction. We will divide our investigation of discussion thread reconstruction into two parts. First, we explore techniques needed to create a corpus for our thread reconstruction research. Like other NLP pairwise classification tasks such as Wikipedia discussion turn/edit alignment and sentence pair text similarity rating, email thread disentanglement is a heavily class-imbalanced problem, and although the advent of crowdsourcing has reduced annotation costs, the common practice of crowdsourcing redundancy is too expensive for class-imbalanced tasks. As the first contribution of this thesis, we evaluate alternative strategies for reducing crowdsourcing annotation redundancy for class-imbalanced NLP tasks. We also examine techniques to learn the best machine classifier from our crowdsourced labels. In order to reduce noise in training data, most natural language crowdsourcing annotation tasks gather redundant labels and aggregate them into an integrated label, which is provided to the classifier. However, aggregation discards potentially useful information from linguistically ambiguous instances. For the second contribution of this thesis, we show that, for four of five natural language tasks, filtering of the training dataset based on crowdsource annotation item agreement improves task performance, while soft labeling based on crowdsource annotations does not improve task performance. Second, we investigate thread reconstruction as divided into the tasks of thread disentanglement and adjacency recognition. We present the Enron Threads Corpus, a newly-extracted corpus of 70,178 multi-email threads with emails from the Enron Email Corpus. In the original Enron Emails Corpus, emails are not sorted by thread. To disentangle these threads, and as the third contribution of this thesis, we perform pairwise classification, using text similarity measures on non-quoted texts in emails. We show that i) content text similarity metrics outperform style and structure text similarity metrics in both a class-balanced and class-imbalanced setting, and ii) although feature performance is dependent on the semantic similarity of the corpus, content features are still effective even when controlling for semantic similarity. To reconstruct threads, it is also necessary to identify adjacency relations among pairs. For the forum of Wikipedia discussions, metadata is not available, and dialogue act typologies, helpful for other domains, are inapplicable. As our fourth contribution, via our experiments, we show that adjacency pair recognition can be performed using lexical pair features, without a dialogue act typology or metadata, and that this is robust to controlling for topic bias of the discussions. Yet, lexical pair features do not effectively model the lexical semantic relations between adjacency pairs. To model lexical semantic relations, and as our fifth contribution, we perform adjacency recognition using extracted keyphrases enhanced with semantically related terms. While this technique outperforms a most frequent class baseline, it fails to outperform lexical pair features or tf-idf weighted cosine similarity. Our investigation shows that this is the result of poor word sense disambiguation and poor keyphrase extraction causing spurious false positive semantic connections. In concluding this thesis, we also reflect on open issues and unanswered questions remaining after our research contributions, discuss applications for thread reconstruction, and suggest some directions for future work. |
||||
Alternatives oder übersetztes Abstract: |
|
||||
Freie Schlagworte: | Natural Language Processing, Discussion Thread Reconstruction, Thread Disentanglement, Adjacency Recognition, Crowdsourcing, Amazon Mechanical Turk, Class-Imbalanced Corpus, Email Threads, Wikipedia Discussions, Enron Threads Corpus, Soft Labeling, Lexical Expansion, Text Classification, Machine Learning | ||||
Schlagworte: |
|
||||
URN: | urn:nbn:de:tuda-tuprints-53850 | ||||
Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik 400 Sprache > 400 Sprache, Linguistik |
||||
Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung 20 Fachbereich Informatik |
||||
Hinterlegungsdatum: | 01 Mai 2016 19:55 | ||||
Letzte Änderung: | 01 Mai 2016 19:55 | ||||
PPN: | |||||
Referenten: | Gurevych, Prof. Dr. Iryna ; Fürnkranz, Prof. Dr. Johannes ; Daelemans, Prof. Walter | ||||
Datum der mündlichen Prüfung / Verteidigung / mdl. Prüfung: | 17 Februar 2016 | ||||
Schlagworte: |
|
||||
Export: | |||||
Suche nach Titel in: | TUfind oder in Google |
Frage zum Eintrag |
Optionen (nur für Redakteure)
Redaktionelle Details anzeigen |