Opinion Holder and Target Extraction on Opinion Compounds – A Linguistic Approach

Proceedings of NAACL-HLT 2016, pages 800–810, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Opinion Holder and Target Extraction on Opinion Compounds – A Linguistic Approach Michael Wiegand and Christine Bocionek Spoken Language Systems Saarland University D-66123 Saarbr¨ucken, Germany michael.wiegand@lsv.uni-saarland.de cbocionek@lsv.uni-saarland.de Josef Ruppenhofer Dept. of Information Science and Language Technology Hildesheim University D-31141 Hildesheim, Germany ruppenho@uni-hildesheim.de Abstract We present an approach to the new task of opinion holder and target extraction on opin- ion compounds. Opinion compounds (e.g. user rating or victim support) are noun com- pounds whose head is an opinion noun. We do not only examine features known to be ef- fective for noun compound analysis, such as paraphrases and semantic classes of heads and modifiers, but also propose novel features tai- lored to this new task. Among them, we ex- amine paraphrases that jointly consider hold- ers and targets, a verb detour in which noun heads are replaced by related verbs, a global head constraint allowing inferencing between different compounds, and the categorization of the sentiment view that the head conveys. 1 Introduction One of the key subtasks in sentiment analysis is opinion role extraction. It can be divided into the extraction of opinion holders (OH), i.e. entities ex- pressing an opinion, and the extraction of opinion targets (OT), i.e. entities or propositions at which sentiment is directed. This task is vital for various applications involving sentiment analysis, e.g. opin- ion summarization or opinion question answering. Opinion role extraction is commonly regarded as a task in lexical semantics. An opinion is evoked by some opinion word, e.g. criticized in (1), skeptical in (2) or intentions in (3), and its opinion roles are usually realized as syntactic dependents. Opinion words come in many shapes, the most frequent types being opinion verbs (1), opinion adjectives (2) and opinion nouns (3). These types of opinion words have extensively been studied in various sentiment- related corpora, such as MPQA (Wiebe et al., 2005). (1) [Peter OH ] criticizedverb [Mary OT ]. (2) [Mary OH ] was skepticaladj [about the plan OT ]. (3) [Peter OH ] had firm intentionsnoun [to quit his job OT ]. In this work, we examine opinion roles that are re- alized in opinion compounds. We define an opinion compound (Table 1) as a noun compound, i.e. a se- quence of two nouns, where the second noun, i.e. the head, is an opinion expression. The first noun, i.e. the modifier, can represent an opinion holder (4)-(5), an opinion target (6)-(7) or neither (8)-(9). Our aim is to automatically classify the modifier into these categories. This task is challenging as, unlike with opinion roles expressed in the syntax (1)-(3), the immediate context of compounds does not con- tain explicit cues as to the relation between head and modifier. Moreover, due to the high productivity of compounding, this task cannot be solved by com- piling a (finite) compound lexicon that encodes for each compound the category of its modifier. (4) [user OH ] rating (i.e. user …

Content truncated to 500 words