Download presentation
Presentation is loading. Please wait.
Published byFay Vanessa Foster Modified over 9 years ago
1
Multi-modal Reference Resolution in Situated Dialogue by Integrating Linguistic and Extra-Linguistic Clues Ryu Iida Masaaki Yasuhara Takenobu Tokunaga Tokyo Institute of Technology IJCNLP 2011 (Nov 9 2011)
2
Research background 2 Typical coreference/anaphora resolution Researchers have tackled problems provided by MUC, ACE and CoNLL shared tasks (a.k.a. OntoNote) Mainly focused on linguistic aspect of reference function Multi-modal research community (Byron, 2005; Prasov and Chai, 2008; Prasov and Chai, 2010; Schütte et al., 2010, Iida et al. 2010) Essential for human-computer interaction Identifying referents of referring expressions in a static scene or a situated world, taking extra-linguistic clues into account
3
Multi-modal reference resolution 3 move the triangle to the left Rotate the triangle at top right 60 degrees clockwise All right… done it.. O.K. dialogue history … piece 1: move (X:230,Y:150) piece 7: move (X:311, Y:510) piece 3: rotate 60° … piece 1: move (X:230,Y:150) piece 7: move (X:311, Y:510) piece 3: rotate 60° action history eye-gaze
4
Aim 4 Integrate several types of multi-modal information into a machine learning-based reference resolution model Investigate which kinds of clues are effective on multi-modal reference resolution
5
Multi-modal problem setting: related work 5 3D virtual world (Byron 2005, Stonia et al. 2008) e.g. Participants controlled an avatar in a virtual world for exploring hidden treasures Frequently occurring scene updates Referring expressions will be relatively skewed to exophoric cases Static scene (Dale 1992) Centrality and size of each object in computer display is fixed through dialogues Change of visual salience of objects is not observed
6
Evaluation data set creation 6 REX-J corpus (Spanger et al. 2010) Dialogues and transcripts of collaborative work (solving Tangram puzzles) by two Japanese participants Designed the puzzle solving task to require the frequent use of both anaphoric and exophoric referring expressions
7
solver operator Setting of collecting data 7 not available shield screen working area goal shape
8
Collecting eye gaze data 8 Recruited 18 Japanese graduate students split them into 9 pairs All pairs knew each other previously and were of the same sex and approximately the same age Introduced to solve 4 different Tangram puzzles Use the Tobii T60 Eye Tracker, sampling at 60 Hz for recording users’ eye gaze with 0.5 degrees in accuracy 5 dialogues in which the tracking results contained more than 40% errors were removed
9
Annotating referring expressions 9 Conducted using a multimedia annotation tool, ELAN Annotator manually detects a referring expression and then selects its referent out of the possible puzzle pieces shown on the computer display Total number of annotated referring expressions: 1,462 instances in 27 dialogues 1,192 instances in solver’s utterances (81.5%) 270 instances in operator’s utterances (18.5%)
10
Multi-modal reference resolution 10 Base model Ranking candidate referents is important for better accuracy (Iida et al. 2003, Yang et al. 2003, Denis & Baldridge 2008) Apply Ranking SVM algorithm (Joachims, 2002) Learn a weight vector to rank candidates for a given partial ranking of each referent Training instances To define the partial ranking of candidate referents, simply rank referents referred to by a given referring expression as first place and any other referents as second place
11
Feature set 11 1. Linguistic features: Ling (Iida et al. 2010): 10 features Capture the linguistic salience of each referent based on the discourse history 2. Task-specific features: TaskSp (Iida et al. 2010):12 features Consider the visual salience based on the recent movements of mouse cursor and recent pieces manipulated by the operator 3. Eye-gaze features: Gaze (proposed):14 features
12
Eye gaze as clues of reference function 12 Eye gaze Saccades: quick, simultaneous movements of both eyes in the same direction Eye-fixations: maintaining of the visual gaze on a single location Direction of eye gaze directly reflects the focus of attention (Richardson et al., 2007) Used the eye fixations as clues for identifying the pieces focused on Separating saccades and eye fixations: Dispersion-threshold identification (Salvucci and Anderson, 2001)
13
Eye gaze features 13 time “First you need to move the smallest triangle to the left” a b c d e f g fixating on piece_b t-T T = 1500msec (Prasov and Chai 2010) t t’ fixating on piece_a how frequently or how long the speaker fixates on each piece
14
Empirical evaluation 14 Compared models with different combinations of the three types of features Conducted 5-fold cross-validation Proposed model with model separation (Iida et al. 2010) the referential behaviour of pronouns is completely different from non-pronouns Separately create two reference resolution models; pronoun model: identifies a referent of a given pronoun non-pronoun model: identifies a referent of all other expressions (e.g. NP)
15
Results of (non-)pronouns 15 modelpronounnon-pronoun Ling56.065.4 Gaze56.748.0 TaskSp79.221.1 Ling+Gaze66.575.7 Ling+TaskSp79.067.1 TaskSp+Gaze78.048.4 Ling+TaskSp+Gaze78.776.0
16
Overall results 16 modelaccuracy Ling61.8 Gaze51.2 TaskSp42.8 Ling+Gaze72.3 Ling+TaskSp71.5 TaskSp+Gaze59.5 Ling+TaskSp+Gaze77.0
17
Investigation of the significance of features 17 Calculate the weight of features according to the following formula set of the support vectors in a ranker weight of the support vector x function that returns 1 if f occurs in x
18
Weights of features in each model 18 pronoun modelnon-pronoun model rankfeatureweightfeatureweight 1TaskSp10.4744Ling60.6149 2TaskSp30.2684Gaze100.1566 3Ling10.2298Gaze90.1566 4TaskSp70.1929Gaze70.1255 5TaskSp90.1605Gaze110.1225 6Gaze100.1547Gaze140.1134 7Gaze90.1547Gaze130.1134 8Ling60.1442Gaze120.1026 9Gaze70.1267Ling20.1014 10Ling20.1164Gaze10.0750 TaskSp1: mouse cursor was over a piece at the beginning of uttering a referring expression TaskSp3: time distance is less than or equal to 10 sec after the mouse cursor was over a piece TaskSp1: mouse cursor was over a piece at the beginning of uttering a referring expression TaskSp3: time distance is less than or equal to 10 sec after the mouse cursor was over a piece
19
Weights of features in each model 19 pronoun modelnon-pronoun model rankfeatureweightfeatureweight 1TaskSp10.4744Ling60.6149 2TaskSp30.2684Gaze100.1566 3Ling10.2298Gaze90.1566 4TaskSp70.1929Gaze70.1255 5TaskSp90.1605Gaze110.1225 6Gaze100.1547Gaze140.1134 7Gaze90.1547Gaze130.1134 8Ling60.1442Gaze120.1026 9Gaze70.1267Ling20.1014 10Ling20.1164Gaze10.0750 Ling6: shape attributes of a piece are compatible with the attributes of a referring expression Gaze10: there exists the fixation time of a piece in the time period [t − T, t] Gaze 9: the fixation time of a piece in the time period [t − T, t] is longest out of all pieces Gaze10: there exists the fixation time of a piece in the time period [t − T, t] Gaze 9: the fixation time of a piece in the time period [t − T, t] is longest out of all pieces
20
Summary 20 Investigated the impact of multi-modal information on reference resolution in Japanese situated dialogues The results demonstrate The referents of pronouns rely on the visual focus of attention such as is indicated by moving the mouse cursor Non-pronouns are strongly related to eye fixations on its referent Integrating these two types of multi-modal information into linguistic information contributes to increasing accuracy of reference resolution
21
Future work 21 Need further data collection All objects in Tangram puzzle (i.e. puzzle pieces) have nearly the same size Rejecting the factor that a relatively larger object occupying the computer display has higher prominence over smaller objects Zero-anaphors in utterances need to be annotated frequent use of them in Japanese
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.