coling 2014: joint opinion relation detection using one-class deep neural network
TRANSCRIPT
Komachi Lab. M1 Peinan ZHANG
Joint Opinion Relation Detection Using One-Class Deep Neural Network COLING 2014 reading @ Komachi Lab
Komachi Lab. M1 Peinan ZHANG
Abstract & Introduction 有効な opinion relation には3つ必要な条件がある。
1. 感情極性を含んだ opinion word 2. 現在のドメインに関連した opinion target 3. opinion word が opinion target を修飾している
これをタプルとして表現すると o = (s, t, r)
となり、それぞれ s = opinion word
t = opinion target
r = linking relation between s and t
2
Komachi Lab. M1 Peinan ZHANG
Assumption 1 Terms are likely to have linking relation with the seed terms are believed to be opinion words or opinion targets.
seed terms とのリンクを持つ単語は opinion words もしくは opinion targets である。
3
Komachi Lab. M1 Peinan ZHANG
Abstract & Introduction Example 1.
This mp3 has a clear screen. s = {clear}, t = {screen}, r = {clear, screen}
Example 2. This mp3 has many good things.
s = {good}, t = {things}, r = {good, things}
Is the word ‘things’ related to the domain ‘mp3’ ?
4
NO!!
o = (s, t, r) s = opinion word t = opinion target r = linking relation between s and t
Komachi Lab. M1 Peinan ZHANG
The Problems 前述した3つの条件
1. 感情極性を含んだ opinion word 2. 現在のドメインに関連した opinion target 3. opinion word が opinion target を修飾している
のうち、2つにのみ焦点を当てていた。 そのため先行研究は雑多なノイズ単語を抽出してしまい、その影響を受けることになった。
Minging Hu and Bing Liu., 2004., Mining and summarizing customer reviews, ACM SIGKDD
5
Komachi Lab. M1 Peinan ZHANG
Assumption 2 The three requirements: the opinion word, the opinion target and the linking relation between them, shall be all verified during opinion relation detection.
3つの必要な条件である opinion word と opinion target 、それらの linking relation は同時に使わなければならない。
6
Komachi Lab. M1 Peinan ZHANG
a novel Joint Opinion Relation Detection Methodopinion words, opinion targets and linking relations are simultaneously considered in a classification scenario.
HOW TO1. provide a small set of seeds for supervision, which are regarded
as positive labeled examples. n small set of seeds: opinion words, opinion targets n negative examples (i.e. noise terms) are hard to acquire, because we
do not know which term is not an opinion word or target. 2. This leads to One-Class Classification (OCC) problem.
n the key to OCC is semantic similarity measuring between terms. n Deep Neural Network (DNN) with word embeddings is a powerful
tool to handle this problem.
Approach
7
Komachi Lab. M1 Peinan ZHANG
a novel Joint Opinion Relation Detection Methodopinion words, opinion targets and linking relations are simultaneously considered in a classification scenario.
HOW TO1. provide a small set of seeds for supervision, which are regarded
as positive labeled examples. n small set: opinion words, opinion targets n negative examples (i.e. noise terms) are hard to acquire, because we
do not know which term is not an opinion word or target. 2. This leads to One-Class Classification (OCC) problem.
n the key to OCC is semantic similarity measuring between terms. n Deep Neural Network (DNN) with word embeddings is a powerful
tool to handle this problem.
Approach
8
Komachi Lab. M1 Peinan ZHANG
The Architecture of OCDNN
9
Consists of two levels. Lower Level: Learn features
n Left uses words embedding to represent opinion words/targets.
n Right maps linking relations to embedding vectors by a recursive auto-encoder
Higher Level: use the learnt feature to perform one-class classification
Komachi Lab. M1 Peinan ZHANG
Outline 1. Abstract & Introduction 2. Approach 3. The Architecture of OCDNN
1. Generate Opinion Seeds 2. Generate Opinion Relation Candidates 3. Represent Words 4. Represent Linking Relation 5. One-Class Classification
4. Datasets & Experiments 5. Conclusion
10
Komachi Lab. M1 Peinan ZHANG
Outline 1. Abstract & Introduction 2. Approach 3. The Architecture of OCDNN
1. Generate Opinion Seeds 2. Generate Opinion Relation Candidates 3. Represent Words 4. Represent Linking Relation 5. One-Class Classification
4. Datasets & Experiments 5. Conclusion
11
Komachi Lab. M1 Peinan ZHANG
Opinion Seed Generation Opinion Word Seeds
We manually pick 186 domain independent opinion words from SentiWordNet as the opinion seed set SS.
Opinion Target Seeds We measure Likelihood Ratio Tests (LRT) between domain name and all opinion target candidates. Then highest N terms with highest LRT scores are added into the opinion target seed set TS.
Linking Relation Seeds We employ an automatic syntactic opinion pattern learning method called Sentiment Graph Walking and get 12 opinion patterns with highest confidence as the linking relation seed set RS.
12
Komachi Lab. M1 Peinan ZHANG
Opinion Relation Candidate Generation Opinion Word Candidates:
p adjectives or verbs
Opinion Target Candidates: p noun or noun phrases
Opinion Relation Candidates: p get dependency tree of a sentence using Stanford Parser p the shortest dependency path between a c_s and a c_t is
taken as a c_r p to avoid introducing too many noise candidates, we
constrain that there are at most 4 terms in a c_r
13
Komachi Lab. M1 Peinan ZHANG
Word Representation by Word Embedding Learning Words are embedded into a hyperspace, where 2 words that are more semantically similar to each other are located closer. (something like word2vec)
See more in the paper below, Ronan Collobert et al., 2011., Natural language processing (almost) from scratch, Journal of Machine Learning Research
14
Komachi Lab. M1 Peinan ZHANG
Linking Relation Representation by Using Recursive Auto-encoder Goal: represent the linking relation between an opinion word and an opinion target by a n-element vector as we do during word representation.
We combined embedding vectors of words in a linking relation by a recursive auto-encoder according to syntactic dependency structure.
15
Komachi Lab. M1 Peinan ZHANG
Linking Relation Representation by Using Recursive Auto-encoder
16
1. c_s と c_t との間の係り受け関係を取ってくる。
2. c_s と c_t をそれぞれ[SC] と [ST] に置き換える。
3. 点線内を3層からなる auto-encoder とし、2つの n-element vector を中間層で1つの n-element vector に圧縮する(下式)。
4. W を入力と出力のユークリッド距離が最小になるまで更新していく。
Example. too loud to listen to the player
Komachi Lab. M1 Peinan ZHANG
One-Class Classification for Opinion Relation Detection We represent an opinion relation candidate c_o by a vector v_o=[v_s; v_t; v_r], and this vector v_o is to feed to upper level auto-encoder.
For opinion relation detection, error scores that are smaller than a threshold theta are classified as positive.
To estimate theta, we need to introduce a positive proportion (pp) score as follows,
17
Komachi Lab. M1 Peinan ZHANG
Opinion Target Expansion We apply bootstrapping to iteratively expand opinion targets seeds.
p because the vocabulary of seed set is limited, which cannot fully represent the distribution of opinion targets.
After training OCDNN, all opinion relation candidates are classified, and opinion targets are ranked in descent order by,
Then, top M candidates are added into the target seed set TS for the next training iteration.
18
Komachi Lab. M1 Peinan ZHANG
Datasets Datasets
p Customer Review Dataset (CRD) n contains review on five products (denoted by D1 to D5)
p benchmark dataset on MP3 and Hotel p crawled from www.amazon.com, which involves Mattress and
Phone Annotation
p 10000 sentences are randomly selected from reviews and annotators are required to judge whether each term is an opinion word or an opinion target.
p 5000 sentences are annotated for MP3 and Hotel. Annotators are required to carefully read through each sentence and find out every opinion relation detection.
19
Komachi Lab. M1 Peinan ZHANG
Evaluation Settings AdjRule
extract opinion words/targets by using adjacency rules
LRTBOOT bootstrapping algorithm which employs Likelihood Ration Test as the co-occurrence statistical measure
DP denotes the Double Propagation algorithm
DP-HITS enhanced version of DP by using HITS algorithm
OCDNN proposed method. The target seed size N=40, the opinion targets expanded in each iteration M=20, and the max bootstrapping iteration number is X=10. 20
statistical co-occurrence-based method
syntax-based method
Komachi Lab. M1 Peinan ZHANG
Experiments DP-HITS does not extract opinion words so their results for opinion words are not taken into account.
21
Komachi Lab. M1 Peinan ZHANG
Experiments
22
Komachi Lab. M1 Peinan ZHANG
Experiments
23
n our method outperforms co-occurrence-based methods AdjRule and LRTBOOT
n but achieves comparable or a little worse results than syntax-based methods DP and DP-HITS n because CRD is quite small, which only contains several
hundred sentences for each product review set. In this case, methods based on careful-designed syntax rules have superiority over those based on statistics.
n our method outperforms all of the competitors n OCDNN vs. DP-HITS: those two use similar term ranking metrics,
but OCDNN significantly outperforms DP-HITS. Therefore, positive proportion is more effective than the importance score.
n OCDNN vs. LRTBOOT: LRTBOOT is better recall but lower precision. This is because LRTBOOT follows Assumption 1, which suffers a lot from error propagation, while our joint classification approach effectively alleviates this issue.
Komachi Lab. M1 Peinan ZHANG
Assumption 1 vs. Assumption 2
24
Komachi Lab. M1 Peinan ZHANG 25
Assumption 1 vs. Assumption 2
n OCDNN significantly outperforms all competitors. The average improvement of F-measure over the best competitor is 6% on CRD and 9% on Hotel and MP3.
n As Assumption 1 only verifies 2 of the requirements, it would inevitably introduce noise terms.
n For syntax-based method DP, it extracts many false opinion relations such as good thing and nice one or objective expressions like another mp3 and every mp3.
n For co-occurrence statistical methods AdjRule and LRTBOOT, it is very hard to deal with ambiguous linking relations. For example, in phrase this mp3 is very good except the size, co-occurrence statistical methods could hardly tell which opinion target does good modify (mp3 or size).
Komachi Lab. M1 Peinan ZHANG
Conclusion p この論文では joint opinion relation detection を One-
Class Deep Neural Network に適応させて分類を行った。
p 特徴的な点は、 opinion words/targets/relations を同時に参照して分類することにある。
p そして実験では、条件の2つしか適応させていなかった手法よりも良い結果を示すことが出来た。
26
Komachi Lab. M1 Peinan ZHANG
Conclusion 1. Abstract & Introduction 2. Approach 3. The Architecture of OCDNN
1. Generate Opinion Seeds 2. Generate Opinion Relation Candidates 3. Represent Words 4. Represent Linking Relation 5. One-Class Classification
4. Datasets & Experiments 5. Conclusion
27