A Unified Feature Representation for Lexical Connotations

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 2145–2163 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 2145 A Unified Feature Representation for Lexical Connotations Emily Allaway Columbia University New York, USA eallaway@cs.columbia.edu Kathleen McKeown Columbia University New York, USA kathy@cs.columbia.edu Abstract Ideological attitudes and stance are often ex- pressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emo- tional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Addi- tionally, we present a method for creating lex- ical representations that capture connotations within the embedding space and show that us- ing the embeddings provides a statistically sig- nificant improvement on the task of stance de- tection when data is limited. 1 Introduction Expressions of ideological attitudes are widespread in today’s online world, influencing how we per- ceive and react to events and people on a daily basis. These attitudes are often expressed through subtle expressions or associations (Somasundaran and Wiebe, 2010; Murakami and Putra, 2010). For example, the sentence “the people opposed gun control” conveys no information about the author’s opinion. However, by adding just one word, “the selfish people opposed gun control”, the author can convey their stance on both gun control (against) and the people who support it (not valuable and dis- liked). Discerning such subtle meaning is crucial for fully understanding and recognizing the hidden influences behind everyday content. Recent studies in NLP have begun to examine these hidden influences through framing in social media and news (Asur and Huberman, 2010; Hart- mann et al., 2019; Klenner, 2017) and style detec- tion in hyperpartisan news (Potthast et al., 2018). Lexical connotations provide a method to study these influences, including stance, in more detail. Selfish people support gun control. negative impact not tangible impolite not valuable negative sentiment Stance: against gun control Figure 1: Connotations of the word “selfish” and the resulting implied stance on the topic “gun control”. Connotations are implied cultural and emotional associations for words that augment their literal meanings (Carpuat, 2015; Feng et al., 2011). Con- notation values are associated with a phrase (e.g., fear is associated with “cancer”) (Feng et al., 2011) and capture a range of nuances, such as whether a phrase is an insult or implies value (see Figure 1). In this paper, we define six new fine-grained connotation aspects for nouns and adjectives, fill- ing a gap in the literature on connotation lexica, which has focused on verbs (Sap et al., 2017; Rashkin et al., 2016, 2017), and coarse-grained polarity (Feng et al., 2011; Kang et al., 2014). We create a new distantly labeled English lexicon that maps nouns and adjectives to our six aspects and show that it aligns well with human judgments. In addition, we show that our lexicon confirms exist- ing hypotheses …

Content truncated to 500 words