01 JIKD 090905 Oard

Email/Speech Project Overview: 

Email/Speech Project Overview Doug Oard and the Project 1 Team

In the beginning …: 

In the beginning … Real tasks Link detection Value estimation Sensemaking Real data Real science Real collaboration Computer Science Electrical Engineering Information Studies

Processing Email and Speech: 

Processing Email and Speech

Processing Email and Speech: 

Processing Email and Speech

Mentioned Name Detection: 

Mentioned Name Detection Alias-i LingPipe No genre-specific training F=0.4 (exact match names) Simple identity resolution Exact match / one address Example: I Can get the Non-Disturbance agreement after it has been executed by you and <ENAMEX id="122" type="ORGANIZATION">Grande.</ENAMEX>. I will fill in the Legal description of the property one I have received it. Please execute and send to: <ENAMEX id="123" type="ORGANIZATION">Grande Communications, 401 Carlson Circle</ENAMEX>, <ENAMEX id="124" type="LOCATION">San Marcos Texas</ENAMEX>, <ENAMEX id="125" type="LOCATION">78666</ENAMEX> <ENAMEX id="126" type="PERSON">Attention Hunter Williams</ENAMEX>.

Detecting Signatures: 

Message-ID: 1173553.1075839993707.JavaMail.evans@thyme> Date: Thu Nov 15 06:27:50 EST 2001 From: Williams III, Bill [bill.williams@enron.com] To: Reyes, Jim [jim.reyes@enron.com] Cc: Bcc: Subject: RE: Congestion Management Revenue for Tuesday Jim, We also received congestion revenue for HE 10 through HE 18. HE18-although it shows nothing from the CAISO on their site (their server went down) is the same as HE17-the CAISO specifically relayed this to me on a recorded line. Thanks, Bill Message-ID: 32623606.1075839993939.JavaMail.evans@thyme> Date: Tue Nov 13 22:35:19 EST 2001 From: Williams III, Bill [bill.williams@enron.com] To: DL-Portland Volume Mgmt [mgmt.dl-portland@enron.com] Cc: Bcc: Subject: Congestion Management Revenue for Tuesday Good afternoon. We have recieved significant amounts of congestion revenue on real-time for 11/13. Please use the inc sheet or CAPS to settle in the morning. The inc sheet has correct pricing and schedule ID's. Thanks, Bill Message-ID: 18997034.1075839993148.JavaMail.evans@thyme> Date: Tue Nov 27 21:30:18 EST 2001 From: Williams III, Bill [bill.williams@enron.com] To: DL-Portland Real Time Shift [shift.dl-portland@enron.com] Cc: Bcc: Subject: CERS Exposure Group- We are currently owed money by CERS (approximately $100,000). We need to net this to a zero by Friday. It is very important that each of you call CERS and purchase energy from them to net this position out. Otherwise--we will see a loss of $100,000. Let's make this problem go away. Thanks, Bill Detecting Signatures

This is a test slidewieth a jupple of lines: 

This is a test slide wieth a jupple of lines

This is a test slidewieth a jupple of lines: 

This is a test slide wieth a jupple of lines

Conversational Threading: 

Conversational Threading Techniques Reply-chain detection In-reply-to header Subject-line reuse Included text String matching Similarity Content Participants Time frame Applications Thread summaries Drill-down Search expansion Clique detection Anomaly detection Gap reconstruction Participant deletion

Encrypted Indexing: 

Encrypted Indexing

Searching an Encrypted Index: 

Searching an Encrypted Index Alice Bob Server Encryption by Alice Search by Bob Query Term “Sender”

Phone Call Transcripts: 

Phone Call Transcripts Message-ID: <24-20010126-19435570-20020114-R> Message-Type: PhoneCall Date: Fri, 26 Jan 2001 19:43:55 -0600 (CST) From: shari.stack@enron.com To: greg.wolfe@enron.com Parties: shari.stack@enron.com, greg.wolfe@enron.com Subject: Snohornish deal, Houston Chronicle Article, Bonuses e-mail, Houston Chronicle Article, Deal, email to Jane King Subject-TimePos: 145, 313, 713, 775, 920, 1018 InCallNames: Christian, Ken Lay, Greg, Chris Foster, Stewie, Stewie, Mike, Mike, Laverado, Mike, Kim, Shari, Greg, Forney, Stewie, Jane King, Shari InCallNames-TimePos: 42, 81, 90, 95, 96, 143, 146, 190, 262, 266, 522, 580, 780, 1007, 1018, 1038, 1067 Keywords: CDWR, email, email Keywords-TimePos: 55, 689, 1038 X-From: Stack, Shari <> X-To: Wolfe, Greg <> X-Parties: Stack, Shari <>, Wolfe, Greg <> X-AudioFile: 24-20010126-19435570-20020114-R.wav X-TranscriptFile: 24-20010126-19435570-20020114-R.txt SHARI STACK: Hey. GREG WOLFE: All right, let me get my fax machine workin'. Uh - [laughs] SHARI: [laughs] She's like, it was so easy, I could make you a lot of money [laughs]. She's like, he said it so desperate. She goes I hate to laugh at people, but - [laughs] GREG: Did you, um, did you, ah, ah tell her about the, ah, that voice mail? SHARI: Yeah, I said - I said Greg [inaudible] he's got the - they got a mob connection [langhs] - his friend threw away the business card after the meeting.[both laughing] SHARI: But, my God - my God, and so anyway, have you talked to Chnstian about this 'cause Christian apparently talked to him twice today. GREG: Oh, he sent a - Christian sent an e-mail shortly after, you know, that, and said we're not doin' business with this guy. SHARI: [laughs] GREG: Ah, so I still don't understand why this guy's trying to get in the middle of us and CDWR and I guess - SHARI: [laughs]

Speech Detectionand Enhancement: 

Speech Detection and Enhancement Detect characteristic spectrotemporal modulation Filter spectrotemporal features of modeled noise Compatible word spotting algorithm developed in collaboration with Hermansky and Morgan (ICSI, Berkeley)

The rest of the story …: 

The rest of the story … 1: Email thread summarization (Bonnie) 1: Text meaning representations (Sergei) 1: NetLens (Catherine) 2: Dynamic social networks (Jen) 2: Identity resolution (Lise) 2: Modeling genre category relationships (VS) 3: Annotation server (TJ) 3: Detecting cross-source references (Dave)

Next Steps: 

Next Steps Foster collaboration around annotation server Projects 1/2/3, USC-ISI, Berkeley, CMU/CALO Focus investment on high-payoff opportunities Detecting email/phone call/attachment/meeting links Robustly linking participants with mentions Rich conversational threading Progressive investment in formative evaluation