What lies beneath: Semantic and syntactic analysis of manually reconstructed spontaneous speech

Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 746–754, Suntec, Singapore, 2-7 August 2009. c⃝2009 ACL and AFNLP What lies beneath: Semantic and syntactic analysis of manually reconstructed spontaneous speech Erin Fitzgerald Johns Hopkins University Baltimore, MD, USA erinf@jhu.edu Frederick Jelinek Johns Hopkins University Baltimore, MD, USA jelinek@jhu.edu Robert Frank Yale University New Haven, CT, USA bob.frank@yale.edu Abstract Spontaneously produced speech text often includes disfluencies which make it diffi- cult to analyze underlying structure. Suc- cessful reconstruction of this text would transform these errorful utterances into fluent strings and offer an alternate mech- anism for analysis. Our investigation of naturally-occurring spontaneous speaker errors aligned to corrected text with manual semantico- syntactic analysis yields new insight into the syntactic and structural semantic differences between spoken and recon- structed language. 1 Introduction In recent years, natural language processing tasks such as machine translation, information extrac- tion, and question answering have been steadily improving, but relatively little of these systems besides transcription have been applied to the most natural form of language input: spontaneous speech. Moreover, there has historically been lit- tle consideration of how to analyze the underlying semantico-syntactic structure of speech. A system would accomplish reconstruction of its spontaneous speech input if its output were to represent, in flawless, fluent, and content- preserved English, the message that the speaker intended to convey (Fitzgerald and Jelinek, 2008; Fitzgerald et al., 2009). Examples of such recon- structions are seen in the following sentence-like units (SUs). EX1: that’s uh that’s a relief becomes that’s a relief EX2: how can you do that without + it’s a catch-22 becomes how can you do that without <ARG> it’s a catch-22 EX3: they like video games some kids do becomes some kids like video games In EX1, reconstruction requires only the dele- tion of a simple filled pause and speaker repetition (or reparandum (Shriberg, 1994)). The second ex- ample shows a restart fragment, where an utter- ance is aborted by the speaker and then restarted with a new train of thought. Reconstruction here requires 1. Detection of an interruption point (denoted + in the example) between the abandoned thought and its replacement, 2. Determination that the abandoned portion contains unique and preservable content and should be made a new sentence rather than be deleted (which would alter meaning) 3. Analysis showing that a required argument must be inserted in order to complete the sen- tence. Finally, in the third example EX3, in order to pro- duce one of the reconstructions given, a system must 1. Detect the anaphoric relationship between “they” and “some kids” 2. Detect the referral of “do” to “like video games” 3. Make the necessary word reorderings and deletion of the less informative lexemes. These examples show varying degrees of diffi- culty for the task of automatic reconstruction. In each case, we also see that semantic analysis of the reconstruction is more straightforward than of the 746 original string directly. Such analysis not only in- …

Content truncated to 500 words