Anything that can improve the life of the hearing impaired is welcome. As Huenerfauth’s experimental data presents, including pauses in animations of American Sign Language (ASL) increases comprehension for ASL signers. The data presented is very detailed, but the main argument that these pauses should be introduced in specific linguistic locations of the phrases, as opposed to just anywhere, is not convincing.

The author states: “ASL signing conveys information at the same rate as spoken English,” citing a work that is more than 35 years old. In the “Future Work” section, the author refers to a 30-year body of work: “These studies have also suggested syntactic, discourse, and emotional features ... that affect speed and timing of ASL.” My obvious question is: Why in future work? Why didn’t the author investigate this important clue in the present, since prosody makes a huge difference in the linguistic treatment of ASL pauses in animations?

The author merely states that it will be necessary to supply some syntactic information, such as “(1) clause/sentence boundaries, (2) part of speech of each sign, (3) syntactic role of each noun, and (4) a syntactic parse tree for each sentence.” Not clarifying how this will be done or “how in future work we may explore computational linguistic techniques for automatically identifying this information in ASL animations” only transfers the onus of unduly using the word “linguistically” to some later work.

The title of Huenerfauth’s paper promises an improved computational system for deaf signers by providing a linguistically motivated system, but only a small section deals with this topic.

The successful use of pauses situated in certain locations, in ASL animations, seems to be of great value to ASL signers. However, “syntactically based” is a more appropriate term than “linguistically motivated.”